Working Papers
2008
65 records found
Bayesian Model Averaging: Theoretical developments and practical applications
Montgomery, Jacob, Nyhan, Brendan
Submitted: 2008-01-22
Keywords: Bayesian model averaging, BMA, model robustness, specification uncertainty
Abstract: (click to show/hide) Political science researchers typically conduct an idiosyncratic search of possible model configurations and then present a single specification to readers. This approach systematically understates the uncertainty of our results, generates concern among readers and reviewers about fragile model specifications, and leads to the estimation of bloated models with huge numbers of controls. Bayesian model averaging (BMA) offers a systematic method for analyzing specification uncertainty and checking the robustness of one's results to alternative model specifications. In this paper, we summarize BMA, review important recent developments in BMA research, and argue for a different approach to using the technique in political science. We then illustrate the methodology by reanalyzing models of voting in U.S. Senate elections and international civil war onset using software that respects statistical conventions within political science.
Montgomery, Jacob, Nyhan, Brendan
Submitted: 2008-01-22
Keywords: Bayesian model averaging, BMA, model robustness, specification uncertainty
Abstract: (click to show/hide) Political science researchers typically conduct an idiosyncratic search of possible model configurations and then present a single specification to readers. This approach systematically understates the uncertainty of our results, generates concern among readers and reviewers about fragile model specifications, and leads to the estimation of bloated models with huge numbers of controls. Bayesian model averaging (BMA) offers a systematic method for analyzing specification uncertainty and checking the robustness of one's results to alternative model specifications. In this paper, we summarize BMA, review important recent developments in BMA research, and argue for a different approach to using the technique in political science. We then illustrate the methodology by reanalyzing models of voting in U.S. Senate elections and international civil war onset using software that respects statistical conventions within political science.
Partisanship, Voting, and the Dopamine D2 Receptor Gene
Dawes, Christopher, Fowler, James
Submitted: 2008-02-01
Keywords: partisanship, voting, turnout, genetic association, dopamine, DRD2
Abstract: (click to show/hide) Previous studies have found that both political orientations (Alford, Funk & Hibbing 2005) and voting behavior (Fowler, Baker & Dawes 2007, Fowler & Dawes 2007) are significantly heritable. In this article we study genetic variation in another important political behavior: partisan attachment. Using the National Longitudinal Study of Adolescent Health, we show that individuals with the A1 allele of the D2 dopamine receptor gene are significantly less likely to identify as a partisan than those with the A2 allele. Further, we find that this gene's association with partisanship also mediates an indirect association between the A1 allele and voter abstention. These results are the first to identify a specific gene that may be responsible for the tendency to join political groups, and they may help to explain correlation in parent and child partisanship and the persistence of partisan behavior over time.
Dawes, Christopher, Fowler, James
Submitted: 2008-02-01
Keywords: partisanship, voting, turnout, genetic association, dopamine, DRD2
Abstract: (click to show/hide) Previous studies have found that both political orientations (Alford, Funk & Hibbing 2005) and voting behavior (Fowler, Baker & Dawes 2007, Fowler & Dawes 2007) are significantly heritable. In this article we study genetic variation in another important political behavior: partisan attachment. Using the National Longitudinal Study of Adolescent Health, we show that individuals with the A1 allele of the D2 dopamine receptor gene are significantly less likely to identify as a partisan than those with the A2 allele. Further, we find that this gene's association with partisanship also mediates an indirect association between the A1 allele and voter abstention. These results are the first to identify a specific gene that may be responsible for the tendency to join political groups, and they may help to explain correlation in parent and child partisanship and the persistence of partisan behavior over time.
Congressional Careers, Committee Assignments, and Seniority Randomization in the U.S. House of Representatives
Kellermann, Michael, Shepsle, Kenneth
Submitted: 2008-02-01
Keywords: Congress, committees, seniority, randomization
Abstract: (click to show/hide) This paper estimates the effects of initial committee seniority on the career ooetcomes of Democratic members of the Hooese of Representatives from 1949 to 2006. When more than one freshman representative is assigned to a committee, positions in the seniority qoeeoee are established by lottery. This ensoeres that qoeeoee positions are oencorrelated in expectation with other legislator characteristics within these grooeps. This natoeral experiment allows oes to estimate the caoesal effect of seniority on a variety of ooetcomes. Lower ranked committee members are less likely to serve as soebcommittee chairs on their initial committee, are more likely to transfer to other committees, and have fewer sponsored bills passed in the joerisdiction of their initial committee. On the other hand, there is little evidence that the seniority randomization has a net effect on reelection, terms of service in the Hooese, or the total noember of sponsored bills passed.
Kellermann, Michael, Shepsle, Kenneth
Submitted: 2008-02-01
Keywords: Congress, committees, seniority, randomization
Abstract: (click to show/hide) This paper estimates the effects of initial committee seniority on the career ooetcomes of Democratic members of the Hooese of Representatives from 1949 to 2006. When more than one freshman representative is assigned to a committee, positions in the seniority qoeeoee are established by lottery. This ensoeres that qoeeoee positions are oencorrelated in expectation with other legislator characteristics within these grooeps. This natoeral experiment allows oes to estimate the caoesal effect of seniority on a variety of ooetcomes. Lower ranked committee members are less likely to serve as soebcommittee chairs on their initial committee, are more likely to transfer to other committees, and have fewer sponsored bills passed in the joerisdiction of their initial committee. On the other hand, there is little evidence that the seniority randomization has a net effect on reelection, terms of service in the Hooese, or the total noember of sponsored bills passed.
Democratic Compromise: A Latent Variable Analysis of Ten Measures of Regime Type
Pemstein, Daniel, Meserve, Stephen, Melton, James
Submitted: 2008-02-07
Keywords: democracy, measurement, democracy measurement, regime, regime type, latent variable analysis, Bayesian latent variable analysis, UDS, Unified Democracy Scores, multi-rater ordinal probit
Abstract: (click to show/hide) Using a Bayesian latent variable approach, we synthesize a new measure of democracy, the Unified Democracy Scores (UDS), from ten extant scales. We accompany this new scale with quantitative estimates of uncertainty, provide estimates of the relative reliability of the constituent indicators, and quantify what the ordinal levels of each of the existing measures mean in relationship to one another. Our method eschews the difficult -- and often arbitrary -- decision to use one existing democracy scale over another in favor of a cumulative approach that allows us to simultaneously leverage the measurement efforts of numerous scholars.
Pemstein, Daniel, Meserve, Stephen, Melton, James
Submitted: 2008-02-07
Keywords: democracy, measurement, democracy measurement, regime, regime type, latent variable analysis, Bayesian latent variable analysis, UDS, Unified Democracy Scores, multi-rater ordinal probit
Abstract: (click to show/hide) Using a Bayesian latent variable approach, we synthesize a new measure of democracy, the Unified Democracy Scores (UDS), from ten extant scales. We accompany this new scale with quantitative estimates of uncertainty, provide estimates of the relative reliability of the constituent indicators, and quantify what the ordinal levels of each of the existing measures mean in relationship to one another. Our method eschews the difficult -- and often arbitrary -- decision to use one existing democracy scale over another in favor of a cumulative approach that allows us to simultaneously leverage the measurement efforts of numerous scholars.
Estimating Treatment Effects in the Presence of Noncompliance and Nonresponse: The Generalized Endogenous Treatment Model
Esterling, Kevin, Neblo, Michael, Lazer, David
Submitted: 2008-02-14
Keywords: Average Treatment Effects, Principal Stratification, Selection on Unobservables, Latent Variable Models, Deliberation Experiment, Political Efficacy
Abstract: (click to show/hide) If ignored, non-compliance with a treatment and nonresponse on outcome measures can bias estimates of treatment effects in a randomized experiment. To identify treatment effects in the case where compliance and response are conditioned on unobservables, we propose the parametric generalized endogenous treatment (GET) model. As a multilevel random effect model, GET improves on current approaches to principal stratification by incorporating behavioral responses within an experiment to measure each subjects' latent compliance type. We use Monte Carlo methods to show GET has a lower MSE for treatment effect estimates than existing approaches to principal stratification that impute, rather than measure, compliance type for subjects assigned to the control. In an application, we use data from a recent field experiment to assess whether exposure to a deliberative session with their member of Congress changes constituents' levels of internal and external efficacy. Since it conditions on subjects' latent compliance type, GET is able to test whether exposure to the treatment is ignorable after balancing on covariates via matching methods. We show that internally efficacious subjects disproportionately select into the deliberative sessions, and that matching apparently does not break the latent dependence between treatment compliance and outcome. The results suggest that exposure to the deliberative sessions improves external, but not internal, efficacy.
Esterling, Kevin, Neblo, Michael, Lazer, David
Submitted: 2008-02-14
Keywords: Average Treatment Effects, Principal Stratification, Selection on Unobservables, Latent Variable Models, Deliberation Experiment, Political Efficacy
Abstract: (click to show/hide) If ignored, non-compliance with a treatment and nonresponse on outcome measures can bias estimates of treatment effects in a randomized experiment. To identify treatment effects in the case where compliance and response are conditioned on unobservables, we propose the parametric generalized endogenous treatment (GET) model. As a multilevel random effect model, GET improves on current approaches to principal stratification by incorporating behavioral responses within an experiment to measure each subjects' latent compliance type. We use Monte Carlo methods to show GET has a lower MSE for treatment effect estimates than existing approaches to principal stratification that impute, rather than measure, compliance type for subjects assigned to the control. In an application, we use data from a recent field experiment to assess whether exposure to a deliberative session with their member of Congress changes constituents' levels of internal and external efficacy. Since it conditions on subjects' latent compliance type, GET is able to test whether exposure to the treatment is ignorable after balancing on covariates via matching methods. We show that internally efficacious subjects disproportionately select into the deliberative sessions, and that matching apparently does not break the latent dependence between treatment compliance and outcome. The results suggest that exposure to the deliberative sessions improves external, but not internal, efficacy.
MPs for Sale? Estimating Returns to Office in Post-War British Politics
Eggers, Andrew, Hainmueller, Jens
Submitted: 2008-03-22
Keywords: regression discontinuity design, RDD, matching, UK, Britain, political economy
Abstract: (click to show/hide) While the role of money in policymaking is a central question in political economy research, surprisingly little attention has been given to the rents politicians actually derive from politics. We use both matching and a regression discontinuity design to analyze an original dataset on the estates of recently deceased British politicians. We find that serving in Parliament roughly doubled the wealth at death of Conservative MPs but had no discernible effect on the wealth of Labour MPs. We argue that Conservative MPs profited from office in a lax regulatory environment by using their political positions to obtain outside work as directors, consultants, and lobbyists, both while in office and after retirement. Our results are consistent with anecdotal evidence on MPs' outside financial dealings but suggest that the magnitude of Conservatives' financial gains from office was larger than has been appreciated.
Eggers, Andrew, Hainmueller, Jens
Submitted: 2008-03-22
Keywords: regression discontinuity design, RDD, matching, UK, Britain, political economy
Abstract: (click to show/hide) While the role of money in policymaking is a central question in political economy research, surprisingly little attention has been given to the rents politicians actually derive from politics. We use both matching and a regression discontinuity design to analyze an original dataset on the estates of recently deceased British politicians. We find that serving in Parliament roughly doubled the wealth at death of Conservative MPs but had no discernible effect on the wealth of Labour MPs. We argue that Conservative MPs profited from office in a lax regulatory environment by using their political positions to obtain outside work as directors, consultants, and lobbyists, both while in office and after retirement. Our results are consistent with anecdotal evidence on MPs' outside financial dealings but suggest that the magnitude of Conservatives' financial gains from office was larger than has been appreciated.
A method for measuring and decomposing electoral bias for the three-party case
Borisyuk, Galina, Johnston, Ron, Rallings, Colin, Thrasher, Michael
Submitted: 2008-03-26
Keywords: electoral bias, decomposition of bias, British parliamentary elections
Abstract: (click to show/hide) The paper provides a method for measuring and decomposing electoral bias for the three-party case. It builds on the two-party method first developed by Ralph Brookes in the late 1950s. Modifications to the original Brookes method developed in the early 1990s were designed to capture the third party effect in the overall distribution of bias but that bias continued to be expressed in terms of the two major parties. Recent general election results in Britain continue to show strong voter support for the third party. This new method specifically considers the three party situation and calculates both overall bias and also its decomposition at the 2005 general election. The results from this new method are then compared with those found by the Brookes method for each election held since 1983.
Borisyuk, Galina, Johnston, Ron, Rallings, Colin, Thrasher, Michael
Submitted: 2008-03-26
Keywords: electoral bias, decomposition of bias, British parliamentary elections
Abstract: (click to show/hide) The paper provides a method for measuring and decomposing electoral bias for the three-party case. It builds on the two-party method first developed by Ralph Brookes in the late 1950s. Modifications to the original Brookes method developed in the early 1990s were designed to capture the third party effect in the overall distribution of bias but that bias continued to be expressed in terms of the two major parties. Recent general election results in Britain continue to show strong voter support for the third party. This new method specifically considers the three party situation and calculates both overall bias and also its decomposition at the 2005 general election. The results from this new method are then compared with those found by the Brookes method for each election held since 1983.
A New Non-Parametric Matching Method for Bias Adjustment with Applications to Economic Evaluations
Sekhon, Jasjeet
Submitted: 2008-05-11
Keywords: semiparametric and nonparametric matching methods, observational studies, randomized controlled trials, health economic evaluation
Abstract: (click to show/hide) In health economic studies that use observational data, a key concern is how to adjust for imbalances in baseline covariates due to the non-random assignment of the programs under evaluation. Traditional methods of covariate adjustment such as regression and propensity score matching are model dependent and often fail to replicate the results of randomized controlled trials. We demonstrate a new non-parametric matching method, Genetic Matching, which is a generalization of propensity score and Mahalanobis distance matching, using two contrasting case studies. In the first, an economic evaluation of a clinical intervention (Pulmonary Artery Catheterization), applying Genetic Matching to observational data replicates the substantive results of a corresponding randomized controlled trial unlike the extant literature. And in the second case study evaluating capitation versus fee-for service, Genetic Matching radically improves balance on baseline covariates and overturns previous conclusions based on traditional methods.
Sekhon, Jasjeet
Submitted: 2008-05-11
Keywords: semiparametric and nonparametric matching methods, observational studies, randomized controlled trials, health economic evaluation
Abstract: (click to show/hide) In health economic studies that use observational data, a key concern is how to adjust for imbalances in baseline covariates due to the non-random assignment of the programs under evaluation. Traditional methods of covariate adjustment such as regression and propensity score matching are model dependent and often fail to replicate the results of randomized controlled trials. We demonstrate a new non-parametric matching method, Genetic Matching, which is a generalization of propensity score and Mahalanobis distance matching, using two contrasting case studies. In the first, an economic evaluation of a clinical intervention (Pulmonary Artery Catheterization), applying Genetic Matching to observational data replicates the substantive results of a corresponding randomized controlled trial unlike the extant literature. And in the second case study evaluating capitation versus fee-for service, Genetic Matching radically improves balance on baseline covariates and overturns previous conclusions based on traditional methods.
Endogeneity in Probit Response Models
Freedman, David, Sekhon, Jasjeet
Submitted: 2008-05-28
Keywords: Bivariate probit, sample selection, identification, indefinite Hessian, optimization
Abstract: (click to show/hide) In this paper, we look at conventional methods for removing endogeneity bias in regression models, including the linear model and the probit model. The usual Heckman two-step procedure should not be used in the probit model: from a theoretical perspective, this procedure is unsatisfactory, and likelihood methods are superior. However, serious numerical problems occur when standard software packages try to maximize the biprobit likelihood function, even if the number of covariates is small. The log likelihood surface may be nearly flat, or may have saddle points with one small positive eigenvalue and several large negative eigenvalues. We draw conclusions for statistical practice. Finally, we describe the conditions under which parameters in the model are identifable; these results appear to be new.
Freedman, David, Sekhon, Jasjeet
Submitted: 2008-05-28
Keywords: Bivariate probit, sample selection, identification, indefinite Hessian, optimization
Abstract: (click to show/hide) In this paper, we look at conventional methods for removing endogeneity bias in regression models, including the linear model and the probit model. The usual Heckman two-step procedure should not be used in the probit model: from a theoretical perspective, this procedure is unsatisfactory, and likelihood methods are superior. However, serious numerical problems occur when standard software packages try to maximize the biprobit likelihood function, even if the number of covariates is small. The log likelihood surface may be nearly flat, or may have saddle points with one small positive eigenvalue and several large negative eigenvalues. We draw conclusions for statistical practice. Finally, we describe the conditions under which parameters in the model are identifable; these results appear to be new.
The playing field shifts: predicting the seats-votes curve in the 2008 U.S. House election
Kastellec, Jonathan, Gelman, Andrew, Chandler, Jamie
Submitted: 2008-06-01
Keywords: Congress, incumbency, partisan bias, seats-votes curve
Abstract: (click to show/hide) This paper predicts the seats-votes curve for the 2008 U.S House elections. We document how the electoral playing field has shifted from a Republican advantage between 1996 and 2004 to a Democratic tilt today. Due to the shift in incumbency advantage from the Republicans to the Democrats, compounded by a greater number of retirements among Republican members, we show that the Democrats now enjoy a partisan bias, and can expect to win more seats than votes for the first time since 1992. While this bias is not as large as the advantage the Republicans held in 2006, it is likely to help the Democrats win more seats than votes and thus expand their majority.
Kastellec, Jonathan, Gelman, Andrew, Chandler, Jamie
Submitted: 2008-06-01
Keywords: Congress, incumbency, partisan bias, seats-votes curve
Abstract: (click to show/hide) This paper predicts the seats-votes curve for the 2008 U.S House elections. We document how the electoral playing field has shifted from a Republican advantage between 1996 and 2004 to a Democratic tilt today. Due to the shift in incumbency advantage from the Republicans to the Democrats, compounded by a greater number of retirements among Republican members, we show that the Democrats now enjoy a partisan bias, and can expect to win more seats than votes for the first time since 1992. While this bias is not as large as the advantage the Republicans held in 2006, it is likely to help the Democrats win more seats than votes and thus expand their majority.
Objections to Bayesian statistics
Gelman, Andrew
Submitted: 2008-06-01
Keywords: comparison of methods, foundations of statistics
Abstract: (click to show/hide) Bayesian inference is one of the more controversial approaches to statistics. The fundamental objections to Bayesian methods are twofold: on one hand, Bayesian methods are presented as an automatic inference engine, and this raises suspicion in anyone with applied experience. The second objection to Bayes comes from the opposite direction and addresses the subjective strand of Bayesian inference. This article presents a series of objections to Bayesian inference, written in the voice of a hypothetical anti-Bayesian statistician. The article is intended to elicit elaborations and extensions of these and other arguments from non-Bayesians and responses from Bayesians who might have different perspectives on these issues.
Gelman, Andrew
Submitted: 2008-06-01
Keywords: comparison of methods, foundations of statistics
Abstract: (click to show/hide) Bayesian inference is one of the more controversial approaches to statistics. The fundamental objections to Bayesian methods are twofold: on one hand, Bayesian methods are presented as an automatic inference engine, and this raises suspicion in anyone with applied experience. The second objection to Bayes comes from the opposite direction and addresses the subjective strand of Bayesian inference. This article presents a series of objections to Bayesian inference, written in the voice of a hypothetical anti-Bayesian statistician. The article is intended to elicit elaborations and extensions of these and other arguments from non-Bayesians and responses from Bayesians who might have different perspectives on these issues.
Why we (usually) don't have to worry about multiple comparisons
Gelman, Andrew, Hill, Jennifer, Yajima, Masanao
Submitted: 2008-06-01
Keywords: Bayesian inference, hierarchical modeling, multiple comparisons, type S error, statistical significance
Abstract: (click to show/hide) The problem of multiple comparisons can disappear when viewed from a Bayesian perspective. We propose building multilevel models in the settings where multiple comparisons arise. These address the multiple comparisons problem and also yield more efficient estimates, especially in settings with low group-level variation, which is where multiple comparisons are a particular concern. Multilevel models perform partial pooling (shifting estimates toward each other), whereas classical procedures typically keep the centers of intervals stationary, adjusting for multiple comparisons by making the intervals wider (or, equivalently, adjusting the p-values corresponding to intervals of fixed width). Multilevel estimates make comparisons more conservative, in the sense that intervals for comparisons are more likely to include zero; as a result, those comparisons that are made with confidence are more likely to be valid.
Gelman, Andrew, Hill, Jennifer, Yajima, Masanao
Submitted: 2008-06-01
Keywords: Bayesian inference, hierarchical modeling, multiple comparisons, type S error, statistical significance
Abstract: (click to show/hide) The problem of multiple comparisons can disappear when viewed from a Bayesian perspective. We propose building multilevel models in the settings where multiple comparisons arise. These address the multiple comparisons problem and also yield more efficient estimates, especially in settings with low group-level variation, which is where multiple comparisons are a particular concern. Multilevel models perform partial pooling (shifting estimates toward each other), whereas classical procedures typically keep the centers of intervals stationary, adjusting for multiple comparisons by making the intervals wider (or, equivalently, adjusting the p-values corresponding to intervals of fixed width). Multilevel estimates make comparisons more conservative, in the sense that intervals for comparisons are more likely to include zero; as a result, those comparisons that are made with confidence are more likely to be valid.
Going beyond the book: Toward critical reading in statistics teaching
Gelman, Andrew
Submitted: 2008-06-01
Keywords: categorical and continuous variables, handedness, menstruation, primary sources, secondary sources, sex ratio, teaching, textbooks, traffic accidents
Abstract: (click to show/hide) We can improve our teaching of statistical examples from books by collecting further data, reading cited articles, and performing further data analysis. This should not come as a surprise, but what might be new is the realization of how close to the surface these research opportunities are: even influential and celebrated books can have examples where more can be learned with a small amount of additional effort. We discuss three examples that have arisen in our own teaching: an introductory textbook that motivated us to think more carefully about categorical and continuous variables; a book for the lay reader that misreported a study of menstruation and accidents; and a monograph on the foundations of probability that overinterpreted statistically insignificant fluctuations in sex ratios.
Gelman, Andrew
Submitted: 2008-06-01
Keywords: categorical and continuous variables, handedness, menstruation, primary sources, secondary sources, sex ratio, teaching, textbooks, traffic accidents
Abstract: (click to show/hide) We can improve our teaching of statistical examples from books by collecting further data, reading cited articles, and performing further data analysis. This should not come as a surprise, but what might be new is the realization of how close to the surface these research opportunities are: even influential and celebrated books can have examples where more can be learned with a small amount of additional effort. We discuss three examples that have arisen in our own teaching: an introductory textbook that motivated us to think more carefully about categorical and continuous variables; a book for the lay reader that misreported a study of menstruation and accidents; and a monograph on the foundations of probability that overinterpreted statistically insignificant fluctuations in sex ratios.
Friendships Moderate an Association Between a Dopamine Gene Variant and Political Ideology
Settle, Jaime, Dawes, Christopher, Hatemi, Peter, Christakis, Nicholas, Fowler, James
Submitted: 2008-06-08
Keywords:
Abstract: (click to show/hide) Scholars in many fields have long noted the importance of social context in the development of political ideology. Recent work suggests that political ideology also has a heritable component, but no specific gene variant associated with political ideology has so far been identified. In this article we hypothesize that individuals with a genetic predisposition towards seeking out new experiences will tend to be more liberal, but only if they are embedded in a social context that provides them with multiple points of view. Using data from the National Longitudinal Study of Adolescent Health, we test this hypothesis by investigating an association between self-reported political ideology and the 7R variant of the dopamine receptor D4 gene (DRD4), which has previously been associated with novelty-seeking. We find that the number of friendships a person has in adolescence is significantly associated with liberal political ideology among those with DRD4-7R. Among those without the gene variant there is no association. This is the first study ever to elaborate a specific gene-environment interaction that contributes to ideological self-identification, and it highlights the importance of incorporating both nature and nurture into the study of politics.
Settle, Jaime, Dawes, Christopher, Hatemi, Peter, Christakis, Nicholas, Fowler, James
Submitted: 2008-06-08
Keywords:
Abstract: (click to show/hide) Scholars in many fields have long noted the importance of social context in the development of political ideology. Recent work suggests that political ideology also has a heritable component, but no specific gene variant associated with political ideology has so far been identified. In this article we hypothesize that individuals with a genetic predisposition towards seeking out new experiences will tend to be more liberal, but only if they are embedded in a social context that provides them with multiple points of view. Using data from the National Longitudinal Study of Adolescent Health, we test this hypothesis by investigating an association between self-reported political ideology and the 7R variant of the dopamine receptor D4 gene (DRD4), which has previously been associated with novelty-seeking. We find that the number of friendships a person has in adolescence is significantly associated with liberal political ideology among those with DRD4-7R. Among those without the gene variant there is no association. This is the first study ever to elaborate a specific gene-environment interaction that contributes to ideological self-identification, and it highlights the importance of incorporating both nature and nurture into the study of politics.
Teaching Bayesian applied statistics to graduate students in political science, sociology, public health, education, economics, ...
Gelman, Andrew
Submitted: 2008-06-13
Keywords: Bayesian statistics, education
Abstract: (click to show/hide) I share some thoughts on teaching applied regression and Bayesian methods to students in political science and other fields.
Gelman, Andrew
Submitted: 2008-06-13
Keywords: Bayesian statistics, education
Abstract: (click to show/hide) I share some thoughts on teaching applied regression and Bayesian methods to students in political science and other fields.
A Compositional-Hierarchical Model of Abstention under Compulsory Voting (poster)
Katz, Gabriel
Submitted: 2008-06-18
Keywords: compulsory voting, abstention, compositional data, hierarchical modelling, MCMC.
Abstract: (click to show/hide) Invalid voting and electoral absenteeism are two important sources of abstention in compulsory voting systems. Previous studies in this area have not considered the correlation between both variables and ignored the compositional nature of the data, potentially leading to unfeasible results and discarding helpful information from an inferential standpoint. In order to overcome these problems, this paper develops a statistical model that accounts for the compositional and hierarchical structure of the data and addresses robustness concerns raised by the use of small samples that are typical in the literature. The model is applied to analyze invalid voting and electoral absenteeism in Brazilian legislative elections between 1945 and 2006 via MCMC simulations. The results show considerable differences in the determinants of both forms of non-voting; while invalid voting was strongly positively related both to political protest and to the existence of important informational barriers to voting, the influence of these variables on absenteeism is less evident. Comparisons based on posterior simulations indicate that the model developed in this paper fits the dataset better than several alternative modeling approaches and leads to different substantive conclusions regarding the effect of different predictors on the both sources of abstention.
Katz, Gabriel
Submitted: 2008-06-18
Keywords: compulsory voting, abstention, compositional data, hierarchical modelling, MCMC.
Abstract: (click to show/hide) Invalid voting and electoral absenteeism are two important sources of abstention in compulsory voting systems. Previous studies in this area have not considered the correlation between both variables and ignored the compositional nature of the data, potentially leading to unfeasible results and discarding helpful information from an inferential standpoint. In order to overcome these problems, this paper develops a statistical model that accounts for the compositional and hierarchical structure of the data and addresses robustness concerns raised by the use of small samples that are typical in the literature. The model is applied to analyze invalid voting and electoral absenteeism in Brazilian legislative elections between 1945 and 2006 via MCMC simulations. The results show considerable differences in the determinants of both forms of non-voting; while invalid voting was strongly positively related both to political protest and to the existence of important informational barriers to voting, the influence of these variables on absenteeism is less evident. Comparisons based on posterior simulations indicate that the model developed in this paper fits the dataset better than several alternative modeling approaches and leads to different substantive conclusions regarding the effect of different predictors on the both sources of abstention.
Matching for Causal Inference Without Balance Checking
Iacus, Stefano, King, Gary, Porro, Giuseppe
Submitted: 2008-06-26
Keywords: Matching, causal inference, observational data, missing data,
Abstract: (click to show/hide) We address a major discrepancy in matching methods for causal inference in observational data. Since these data are typically plentiful, the goal of matching is to reduce bias and only secondarily to keep variance low. However, most matching methods seem designed for the opposite problem, guaranteeing sample size ex ante but limiting bias by controlling for covariates through reductions in the imbalance between treated and control groups only ex post and only sometimes. (The resulting practical difficulty may explain why many published applications do not check whether imbalance was reduced and so may not even be decreasing bias.) We introduce a new class of "Monotonic Imbalance Bounding" (MIB) matching methods that enables one to choose a fixed level of maximum imbalance, or to reduce maximum imbalance for one variable without changing it for the others. We then discuss a specific MIB method called "Coarsened Exact Matching" (CEM) which, unlike most existing approaches, also explicitly bounds through ex ante user choice both the degree of model dependence and the causal effect estimation error, eliminates the need for a separate procedure to restrict data to common support, meets the congruence principle, is approximately invariant to measurement error, works well with modern methods of imputation for missing data, is computationally efficient even with massive data sets, and is easy to understand and use. This method can improve causal inferences in a wide range of applications, and may be preferred for simplicity of use even when it is possible to design superior methods for particular problems. We also make available open source software which implements all our suggestions.
Iacus, Stefano, King, Gary, Porro, Giuseppe
Submitted: 2008-06-26
Keywords: Matching, causal inference, observational data, missing data,
Abstract: (click to show/hide) We address a major discrepancy in matching methods for causal inference in observational data. Since these data are typically plentiful, the goal of matching is to reduce bias and only secondarily to keep variance low. However, most matching methods seem designed for the opposite problem, guaranteeing sample size ex ante but limiting bias by controlling for covariates through reductions in the imbalance between treated and control groups only ex post and only sometimes. (The resulting practical difficulty may explain why many published applications do not check whether imbalance was reduced and so may not even be decreasing bias.) We introduce a new class of "Monotonic Imbalance Bounding" (MIB) matching methods that enables one to choose a fixed level of maximum imbalance, or to reduce maximum imbalance for one variable without changing it for the others. We then discuss a specific MIB method called "Coarsened Exact Matching" (CEM) which, unlike most existing approaches, also explicitly bounds through ex ante user choice both the degree of model dependence and the causal effect estimation error, eliminates the need for a separate procedure to restrict data to common support, meets the congruence principle, is approximately invariant to measurement error, works well with modern methods of imputation for missing data, is computationally efficient even with massive data sets, and is easy to understand and use. This method can improve causal inferences in a wide range of applications, and may be preferred for simplicity of use even when it is possible to design superior methods for particular problems. We also make available open source software which implements all our suggestions.
Using Item Response Theory to Estimate Ideology in Congress
Kropko, Jonathan
Submitted: 2008-06-28
Keywords: Item Response Theory, Congress, Ideology
Abstract: (click to show/hide) I use item response theory (IRT) to estimate latent ideology from selected roll-call votes in the first session of the 110th House of Representatives. Votes are selected if they are divisive, unique, but not wholly explained by party loyalties. The method is similar to the one employed by Clinton et al (2004), but does not assume a spatial structure of voting. The results demonstrate that (1) although Democrats hold a majority of the seats in the 110th House, a majority of the members have conservative ideologies, (2) the Republican party leadership is much more conservative than the Democratic party leadership is liberal, and (3) that the House is far less ideologically polarized than DW-Nominate scores would indicate.
Kropko, Jonathan
Submitted: 2008-06-28
Keywords: Item Response Theory, Congress, Ideology
Abstract: (click to show/hide) I use item response theory (IRT) to estimate latent ideology from selected roll-call votes in the first session of the 110th House of Representatives. Votes are selected if they are divisive, unique, but not wholly explained by party loyalties. The method is similar to the one employed by Clinton et al (2004), but does not assume a spatial structure of voting. The results demonstrate that (1) although Democrats hold a majority of the seats in the 110th House, a majority of the members have conservative ideologies, (2) the Republican party leadership is much more conservative than the Democratic party leadership is liberal, and (3) that the House is far less ideologically polarized than DW-Nominate scores would indicate.
Measurement Error as a Threat to Causal Inference: Acquiescence Bias and Deliberative Polling
Weiksner, G. Michael
Submitted: 2008-06-29
Keywords: Causal inference, experiments, acquiescence bias, deliberative polling, measurement error, questionnaire design
Abstract: (click to show/hide) Experiments, unlike observational studies, are rarely criticized for yielding invalid causal inferences. However, I identify measurement error as a threat to causal inference of an experiment. In particular, acquiescence bias, a common and substantial source of measurement error within surveys, may be correlated with experimental manipulations. Using data from a survey experiment embedded in a Deliberative Poll, I find that acquiescence bias causes significant measurement error and that the bias differs before and after deliberation. I conclude that even experimental researchers should heed the recommendation by questionnaire design researchers to refrain from asking agree/disagree questions completely and instead ask only construct-specific questions to avoid this threat to validity.
Weiksner, G. Michael
Submitted: 2008-06-29
Keywords: Causal inference, experiments, acquiescence bias, deliberative polling, measurement error, questionnaire design
Abstract: (click to show/hide) Experiments, unlike observational studies, are rarely criticized for yielding invalid causal inferences. However, I identify measurement error as a threat to causal inference of an experiment. In particular, acquiescence bias, a common and substantial source of measurement error within surveys, may be correlated with experimental manipulations. Using data from a survey experiment embedded in a Deliberative Poll, I find that acquiescence bias causes significant measurement error and that the bias differs before and after deliberation. I conclude that even experimental researchers should heed the recommendation by questionnaire design researchers to refrain from asking agree/disagree questions completely and instead ask only construct-specific questions to avoid this threat to validity.
Causal Inference with Differential Measurement Error: Nonparametric Identification and Sensitivity Analyses of a Field Experiment on Democratic Deliberations
Imai, Kosuke, Yamamoto, Teppei
Submitted: 2008-06-30
Keywords: differential misclassification, nonparametric bounds, retrospective studies, sensitivity analysis, survey measurements
Abstract: (click to show/hide) Political scientists have long been concerned about the validity of survey measurements. Although many have studied classical measurement error in linear regression models where the error is assumed to arise completely at random, in a number of situations the error may be correlated with the outcome. We analyze the impact of differential measurement error on causal estimation. The proposed nonparametric identification analysis avoids arbitrary modeling decisions and formally characterizes the roles of additional assumptions. We show the serious consequences of differential misclassification and offer a new sensitivity analysis that allows researchers to evaluate the robustness of their conclusions. Our methods are motivated by a field experiment on democratic deliberations, in which one set of estimates potentially suffers from differential misclassification. We show that an analysis ignoring differential measurement error may considerably overestimate the causal effects. This finding contrasts with the case of classical measurement error which always yields attenuation bias.
Imai, Kosuke, Yamamoto, Teppei
Submitted: 2008-06-30
Keywords: differential misclassification, nonparametric bounds, retrospective studies, sensitivity analysis, survey measurements
Abstract: (click to show/hide) Political scientists have long been concerned about the validity of survey measurements. Although many have studied classical measurement error in linear regression models where the error is assumed to arise completely at random, in a number of situations the error may be correlated with the outcome. We analyze the impact of differential measurement error on causal estimation. The proposed nonparametric identification analysis avoids arbitrary modeling decisions and formally characterizes the roles of additional assumptions. We show the serious consequences of differential misclassification and offer a new sensitivity analysis that allows researchers to evaluate the robustness of their conclusions. Our methods are motivated by a field experiment on democratic deliberations, in which one set of estimates potentially suffers from differential misclassification. We show that an analysis ignoring differential measurement error may considerably overestimate the causal effects. This finding contrasts with the case of classical measurement error which always yields attenuation bias.
A Spatial Model of Electoral Platforms
Elff, Martin
Submitted: 2008-07-01
Keywords: Parties, party families, electoral platforms, party manifestos, spatial models, unobserved data, latent trait models, EM algorithm, Monte Carlo integration, Monte Carlo EM, importance sampling, SIR algorithm, ideological dimensions
Abstract: (click to show/hide) The reconstruction of political positions of parties, candidates and governments has made considerable headway during the last decades, not the least due to the efforts of the Manifesto Research Group the and Comparative Manifestos Project, which compiled and published a data set on the electoral platforms of political parties from most major democracies for most of the post-war era. A central assumption underlying the coding of electoral platforms into quantitative data as done by the MRG/CMP is that parties take positions by selective emphases of policy objectives, which put their accomplishments in a most positive light (Budge 2001) or are representative for their current polital/ideological positions. Consequently, the MRG/CMP data consist of percentages of the respective manifesto texts that refer to various policy objectives. As a consequence both of this underlying assumption and of the structure of the CMP data, methods of classical multivariate analysis are not well suited to these data, due to the requirements to the data for an appropriate application of these methods (van der Brug 2001; Elff 2002). The paper offers an alternative method for reconstructing positions in political spaces based on latent trait modelling, which both re�ects the assumptions underlying the coding of the texts and the peculiar structure of the data. Finally, the validity of the proposed method is demonstrated with respect to the average position of party families within reconstructed policy spaces. It turns out that communist, socialist, and social democrat parties differ clearly from �bourgeois� parties with regards to their positions on an economic left/right dimension, while British and Scandinavian conservative parties can be distinguished from Christian democratic parties by their respective positions on a libertarian/authoritarian and a traditionalist/modernist dimension. Similarly, the typical political positions of green (or �New Politics�) parties can be distinguished from the positions of other party families.
Elff, Martin
Submitted: 2008-07-01
Keywords: Parties, party families, electoral platforms, party manifestos, spatial models, unobserved data, latent trait models, EM algorithm, Monte Carlo integration, Monte Carlo EM, importance sampling, SIR algorithm, ideological dimensions
Abstract: (click to show/hide) The reconstruction of political positions of parties, candidates and governments has made considerable headway during the last decades, not the least due to the efforts of the Manifesto Research Group the and Comparative Manifestos Project, which compiled and published a data set on the electoral platforms of political parties from most major democracies for most of the post-war era. A central assumption underlying the coding of electoral platforms into quantitative data as done by the MRG/CMP is that parties take positions by selective emphases of policy objectives, which put their accomplishments in a most positive light (Budge 2001) or are representative for their current polital/ideological positions. Consequently, the MRG/CMP data consist of percentages of the respective manifesto texts that refer to various policy objectives. As a consequence both of this underlying assumption and of the structure of the CMP data, methods of classical multivariate analysis are not well suited to these data, due to the requirements to the data for an appropriate application of these methods (van der Brug 2001; Elff 2002). The paper offers an alternative method for reconstructing positions in political spaces based on latent trait modelling, which both re�ects the assumptions underlying the coding of the texts and the peculiar structure of the data. Finally, the validity of the proposed method is demonstrated with respect to the average position of party families within reconstructed policy spaces. It turns out that communist, socialist, and social democrat parties differ clearly from �bourgeois� parties with regards to their positions on an economic left/right dimension, while British and Scandinavian conservative parties can be distinguished from Christian democratic parties by their respective positions on a libertarian/authoritarian and a traditionalist/modernist dimension. Similarly, the typical political positions of green (or �New Politics�) parties can be distinguished from the positions of other party families.
Non-ignorable abstentions in roll call data analysis
Rosas, Guillermo, Shomer, Yael
Submitted: 2008-07-02
Keywords: ignorability, IRT model, roll call data, legislative voting
Abstract: (click to show/hide) How should we deal with abstentions in roll-call data analysis? Abstentions are very common in decision-making bodies around the world, and very often obey to a strategic rationale. Methods to recover ideal points from roll-call datasets -- such as Nominate and MCMC IRT -- are based on assumptions about the ignorability of the abstention- generating mechanism. However, the strategic character of abstentions makes the assumption of ignorability difficult to meet in practice. We discuss different abstention-generating mechanisms to understand the conditions under which they may be deemed ignorable, and extend the MCMC IRT model so as to incorporate information from abstention patterns into inference about legislators' ideal points.
Rosas, Guillermo, Shomer, Yael
Submitted: 2008-07-02
Keywords: ignorability, IRT model, roll call data, legislative voting
Abstract: (click to show/hide) How should we deal with abstentions in roll-call data analysis? Abstentions are very common in decision-making bodies around the world, and very often obey to a strategic rationale. Methods to recover ideal points from roll-call datasets -- such as Nominate and MCMC IRT -- are based on assumptions about the ignorability of the abstention- generating mechanism. However, the strategic character of abstentions makes the assumption of ignorability difficult to meet in practice. We discuss different abstention-generating mechanisms to understand the conditions under which they may be deemed ignorable, and extend the MCMC IRT model so as to incorporate information from abstention patterns into inference about legislators' ideal points.
Modeling Sample Selection for Durations with Time-Varying Covariates
Boehmke, Frederick
Submitted: 2008-07-02
Keywords: selection, selection bias, duration, time-vary covariates, event history, exchange rates
Abstract: (click to show/hide) We extend previous estimators for duration data that suffer from non-random sample selection to allow for time-varying covariates. Rather that a continuous-time duration model, we propose a discrete-time alternative that models the (constant) effects of sample selection at the time of selection across all years of the resulting spell. Properties of the estimator are compared to those of a naive discrete duration model through Monte Carlo analysis and indicate that our estimator outperforms the naive model when selection is non-trivial. We then apply this estimator to the question of the duration of monetary regimes.
Boehmke, Frederick
Submitted: 2008-07-02
Keywords: selection, selection bias, duration, time-vary covariates, event history, exchange rates
Abstract: (click to show/hide) We extend previous estimators for duration data that suffer from non-random sample selection to allow for time-varying covariates. Rather that a continuous-time duration model, we propose a discrete-time alternative that models the (constant) effects of sample selection at the time of selection across all years of the resulting spell. Properties of the estimator are compared to those of a naive discrete duration model through Monte Carlo analysis and indicate that our estimator outperforms the naive model when selection is non-trivial. We then apply this estimator to the question of the duration of monetary regimes.
Model Specification in Instrumental-Variables Regression
Dunning, Thad
Submitted: 2008-07-03
Keywords: Instrumental-Variables Least Squares (IVLS) regression; model specification; specification error; homogenous partial effects
Abstract: (click to show/hide) In many applications of instrumental-variables regression, researchers seek to defend the plausibility of a key assumption: the instrumental variable is independent of the error term in a linear regression model. Although fulfilling this exogeneity criterion is necessary for a valid application of the instrumental variables approach, it is not sufficient. In the regression context, the identification of causal effects depends not just on the exogeneity of the instrument but also on the validity of the underlying model. In this paper, I focus on one feature of such models: the assumption that variation in the endogenous regressor that is related to the instrumental variable has the same effect as variation that is unrelated to the instrument. In many applications, this assumption may be quite strong, but relaxing it can limit our ability to estimate parameters of interest. After discussing two substantive examples, I develop analytic results (simulations are reported elsewhere). I also present a specification test that may be useful for determining the relevance of these issues in a given application.
Dunning, Thad
Submitted: 2008-07-03
Keywords: Instrumental-Variables Least Squares (IVLS) regression; model specification; specification error; homogenous partial effects
Abstract: (click to show/hide) In many applications of instrumental-variables regression, researchers seek to defend the plausibility of a key assumption: the instrumental variable is independent of the error term in a linear regression model. Although fulfilling this exogeneity criterion is necessary for a valid application of the instrumental variables approach, it is not sufficient. In the regression context, the identification of causal effects depends not just on the exogeneity of the instrument but also on the validity of the underlying model. In this paper, I focus on one feature of such models: the assumption that variation in the endogenous regressor that is related to the instrumental variable has the same effect as variation that is unrelated to the instrument. In many applications, this assumption may be quite strong, but relaxing it can limit our ability to estimate parameters of interest. After discussing two substantive examples, I develop analytic results (simulations are reported elsewhere). I also present a specification test that may be useful for determining the relevance of these issues in a given application.
Estimating and Bounding Mechanism Specific Causal Effects
Glynn, Adam
Submitted: 2008-07-03
Keywords: counterfactuals, causal, mechanism
Abstract: (click to show/hide) Political scientists often cite the importance of mechanism specific causal knowledge, both for its intrinsic scientific value and as a necessity for informed policy. However, outside the framework of additive linear regression models with homogenous causal effects, mechanism specific effects are, in general, not estimated explicitly. Counterfactual causal models allow the formal definition of such concepts as direct, indirect, and mechanism specific effects, and the derivation of conditions for their identification (point or interval). In this paper, I demonstrate the use of counterfactuals to decompose causal effects into mechanism specific effects, showing that estimation and bounding can be accomplished with minor adjustments to standard techniques. I illustrate this methodology with examples from American and Comparative Politics.
Glynn, Adam
Submitted: 2008-07-03
Keywords: counterfactuals, causal, mechanism
Abstract: (click to show/hide) Political scientists often cite the importance of mechanism specific causal knowledge, both for its intrinsic scientific value and as a necessity for informed policy. However, outside the framework of additive linear regression models with homogenous causal effects, mechanism specific effects are, in general, not estimated explicitly. Counterfactual causal models allow the formal definition of such concepts as direct, indirect, and mechanism specific effects, and the derivation of conditions for their identification (point or interval). In this paper, I demonstrate the use of counterfactuals to decompose causal effects into mechanism specific effects, showing that estimation and bounding can be accomplished with minor adjustments to standard techniques. I illustrate this methodology with examples from American and Comparative Politics.
Causal Inference of Repeated Observations: A Synthesis of the Propensity Score Methods and Multilevel Modeling
Su, Yu-Sung
Submitted: 2008-07-03
Keywords: causal inference, balancing score, multilevel modeling, propensity score, time-series-cross-sectional data
Abstract: (click to show/hide) The fundamental problem of causal inference is that an individual cannot be simultaneously observed in both the treatment and control states (Holland 1986). The propensity score methods that compare the treatment and control groups by discarding the unmatched units are now widely used to deal with this problem. In some situations, however, it is possible to observe the same individual or unit of observation in the treatment and control states at different points in time. The data has the structure that is often refer to as time-series-cross-sectional (TSCS) data. While multilevel modeling is often applied to analyze TSCS data, this paper proposes that synthesizing the propensity score methods and multilevel modeling is preferable. The paper conducts a Monte Carlo simulation with 36 different scenarios to test the performance of the two combined methods. The result shows that synthesizing the propensity score matching with multilevel modeling performs better in that such method yields less biased and more efficient estimates. An empirical case study that reexamine the model of Przeworksi et al (2000) on democratization and development also shows the advantage of this synthesis.
Su, Yu-Sung
Submitted: 2008-07-03
Keywords: causal inference, balancing score, multilevel modeling, propensity score, time-series-cross-sectional data
Abstract: (click to show/hide) The fundamental problem of causal inference is that an individual cannot be simultaneously observed in both the treatment and control states (Holland 1986). The propensity score methods that compare the treatment and control groups by discarding the unmatched units are now widely used to deal with this problem. In some situations, however, it is possible to observe the same individual or unit of observation in the treatment and control states at different points in time. The data has the structure that is often refer to as time-series-cross-sectional (TSCS) data. While multilevel modeling is often applied to analyze TSCS data, this paper proposes that synthesizing the propensity score methods and multilevel modeling is preferable. The paper conducts a Monte Carlo simulation with 36 different scenarios to test the performance of the two combined methods. The result shows that synthesizing the propensity score matching with multilevel modeling performs better in that such method yields less biased and more efficient estimates. An empirical case study that reexamine the model of Przeworksi et al (2000) on democratization and development also shows the advantage of this synthesis.
Estimating Proposal and Status Quo Locations Using Voting and Cosponsorship Data
Peress, Michael
Submitted: 2008-07-04
Keywords: Ideal Point Estimation, Cosponsorship, Status Quo, Theories of Lawmaking
Abstract: (click to show/hide) Theories of lawmaking generate predictions for the policy outcome as a function of the status quo. These theories are difficult to test because existing ideal point estimation techniques do not recover the locations of proposals or status quos. Instead, such techniques only recover cutpoints. This limitation has meant that existing tests of theories of lawmaking have been indirect in nature. I propose a method of directly measuring ideal points, proposal locations, and status quo locations on the same multidimensional scale, by employing a combination of voting data, bill and amendment cosponsorship data, and the congressional record. My approach works as follows. First, we can identify the locations of legislative proposals (bills and amendments) on the same scale as voter ideal points by jointly scaling voting and cosponsorship data. Next, we can identify the location of the final form of the bill using the location of last successful amendment (which we already know). If the bill was not amended, then the final form is simply the original bill location. Finally, we can identify the status quo point by employing the cutpoint we get form scaling the final passage vote. To implement this procedure, I automatically coded data on the congressional record available from www.thomas.gov. I apply this approach to recent sessions of the U.S. Senate, and use it to test the implications of competing theories of lawmaking.
Peress, Michael
Submitted: 2008-07-04
Keywords: Ideal Point Estimation, Cosponsorship, Status Quo, Theories of Lawmaking
Abstract: (click to show/hide) Theories of lawmaking generate predictions for the policy outcome as a function of the status quo. These theories are difficult to test because existing ideal point estimation techniques do not recover the locations of proposals or status quos. Instead, such techniques only recover cutpoints. This limitation has meant that existing tests of theories of lawmaking have been indirect in nature. I propose a method of directly measuring ideal points, proposal locations, and status quo locations on the same multidimensional scale, by employing a combination of voting data, bill and amendment cosponsorship data, and the congressional record. My approach works as follows. First, we can identify the locations of legislative proposals (bills and amendments) on the same scale as voter ideal points by jointly scaling voting and cosponsorship data. Next, we can identify the location of the final form of the bill using the location of last successful amendment (which we already know). If the bill was not amended, then the final form is simply the original bill location. Finally, we can identify the status quo point by employing the cutpoint we get form scaling the final passage vote. To implement this procedure, I automatically coded data on the congressional record available from www.thomas.gov. I apply this approach to recent sessions of the U.S. Senate, and use it to test the implications of competing theories of lawmaking.
Scaling the Critics: Uncovering the Latent Dimensions of Movie Criticism with An Item Response Approach
Peress, Michael, Spirling, Arthur
Submitted: 2008-07-04
Keywords: threshold utility model, film, ideal points
Abstract: (click to show/hide) We study the critical opinions of expert movie reviewers as an item response problem. We develop a framework that models an individual's decision to approve or disapprove of an item. Using this framework, we are able to recover the locations of movies and ideal points of critics in the same multi-dimensional space. We demonstrate that a three dimensional model captures much of the variation in critical opinions. The first dimension signifies movie 'quality' while the other two connote the nature and subject matter of the films. We then demonstrate that the dimensions uncovered from our 'threshold utility model' are statistically significant predictors of a movie's success, and are particularly useful in predicting the success of `independent' films.
Peress, Michael, Spirling, Arthur
Submitted: 2008-07-04
Keywords: threshold utility model, film, ideal points
Abstract: (click to show/hide) We study the critical opinions of expert movie reviewers as an item response problem. We develop a framework that models an individual's decision to approve or disapprove of an item. Using this framework, we are able to recover the locations of movies and ideal points of critics in the same multi-dimensional space. We demonstrate that a three dimensional model captures much of the variation in critical opinions. The first dimension signifies movie 'quality' while the other two connote the nature and subject matter of the films. We then demonstrate that the dimensions uncovered from our 'threshold utility model' are statistically significant predictors of a movie's success, and are particularly useful in predicting the success of `independent' films.
How Similar Are They? Rethinking Electoral Congruence
Wittenberg, Jason
Submitted: 2008-07-05
Keywords: voting, elections, volatility, persistence, correlation, concordance
Abstract: (click to show/hide) Electoral continuity and discontinuity have been a staple of voting research for decades. Most researchers have employed Pearson's r as a measure of congruence between two electoral outcomes across a set of geographic units. This paper argues that that practice should be abandoned. The correlation coefficient is almost always the wrong measure. The paper recommends other quantities that better accord with what researchers usually mean by electoral persistence. Replications of prior studies in American and comparative politics demonstrate that the consequences of using r when it is inappropriate can be stark. In some cases what we think are continuities are actually discontinuities.
Wittenberg, Jason
Submitted: 2008-07-05
Keywords: voting, elections, volatility, persistence, correlation, concordance
Abstract: (click to show/hide) Electoral continuity and discontinuity have been a staple of voting research for decades. Most researchers have employed Pearson's r as a measure of congruence between two electoral outcomes across a set of geographic units. This paper argues that that practice should be abandoned. The correlation coefficient is almost always the wrong measure. The paper recommends other quantities that better accord with what researchers usually mean by electoral persistence. Replications of prior studies in American and comparative politics demonstrate that the consequences of using r when it is inappropriate can be stark. In some cases what we think are continuities are actually discontinuities.
Binary and Ordinal Time Series with AR(p) Errors: Bayesian Model Determination for Latent High-Order Markovian Processes
Pang, Xun
Submitted: 2008-07-06
Keywords: Autoregressive Errors, Auxiliary Particle Filter, Fixed-lag Smoothing, Markov Chain Monte Carlo (MCMC), Political Science, Sampling Importance Resampling(SIR)
Abstract: (click to show/hide) To directly and adequately correct serial correlation in binary and ordinal response data, this paper proposes a probit model with errors following a pth-order autoregressive process, and develops simulation-based methods in the Bayesian context to handle computational challenges of posterior estimation, model comparison, and lag order determination. Compared to the extant methods, such as quasi-ML, GCM, and and simulation-based ML estimators, the current method does not rely on the properties of the big variance-covariance matrix or the shape of the likelihood function. In addition, the present model efficiently handles high-order autocorrelated errors that raise computationally formidable difficulties to the conventional methods. By applying a mixed sampler of the Gibbs and Metropolis-Hastings algorithm, the posterior distributions of the parameters do not depend on initial observations. The auxiliary particle filter, complemented by the fixed-lag smoothing, is extended to approximate Bayes Factors for models with latent high-order Markov processes. Computational methods are tested with empirical data. Energy cooperation policies of the International Energy Agency are analyzed in terms of their effects on global oil-supply security. The current model with different lag orders, together with other competitive models, is estimated and compared.
Pang, Xun
Submitted: 2008-07-06
Keywords: Autoregressive Errors, Auxiliary Particle Filter, Fixed-lag Smoothing, Markov Chain Monte Carlo (MCMC), Political Science, Sampling Importance Resampling(SIR)
Abstract: (click to show/hide) To directly and adequately correct serial correlation in binary and ordinal response data, this paper proposes a probit model with errors following a pth-order autoregressive process, and develops simulation-based methods in the Bayesian context to handle computational challenges of posterior estimation, model comparison, and lag order determination. Compared to the extant methods, such as quasi-ML, GCM, and and simulation-based ML estimators, the current method does not rely on the properties of the big variance-covariance matrix or the shape of the likelihood function. In addition, the present model efficiently handles high-order autocorrelated errors that raise computationally formidable difficulties to the conventional methods. By applying a mixed sampler of the Gibbs and Metropolis-Hastings algorithm, the posterior distributions of the parameters do not depend on initial observations. The auxiliary particle filter, complemented by the fixed-lag smoothing, is extended to approximate Bayes Factors for models with latent high-order Markov processes. Computational methods are tested with empirical data. Energy cooperation policies of the International Energy Agency are analyzed in terms of their effects on global oil-supply security. The current model with different lag orders, together with other competitive models, is estimated and compared.
Adjusting Experimental Data
Keele, Luke, McConnaughy, Corrine, White, Ismail
Submitted: 2008-07-06
Keywords: Experiments, matching, ANCOVA, blocking
Abstract: (click to show/hide) Randomization in experiments allows researchers to assume that the treatment and control groups are balanced with respect to all characteristics except the treatment. Randomization, however, only makes balance probable, and accidental covariate imbalance can occur for any specific randomization. As such, statistical adjustments for accidental imbalance are common with experimental data. The most common method of adjustment for accidental imbalance is to use least squares to estimate the analysis of covariance (ANCOVA) model. ANCOVA, however, is a poor choice for the adjustment of experimental data. It has a strong functional form assumption, and the least squares estimator is notably biased in sample sizes of less than 500 when applied to the analysis of treatment effects. We evaluate alternative methods of adjusting experimental data. We compare ANCOVA to two different techniques. The first technique is a modified version of ANCOVA that relaxes the strong functional form assumption of this model. The second technique is matching, and we test the differences between two matching methods. For the first, we match subjects and then randomize treatment across pairs. For the second, we randomize the treatment and match prior to the estimation of treatment effects. We use all three techniques with data from a series of experiments on racial priming. We find that matching substantially increases the efficiency of experimental designs.
Keele, Luke, McConnaughy, Corrine, White, Ismail
Submitted: 2008-07-06
Keywords: Experiments, matching, ANCOVA, blocking
Abstract: (click to show/hide) Randomization in experiments allows researchers to assume that the treatment and control groups are balanced with respect to all characteristics except the treatment. Randomization, however, only makes balance probable, and accidental covariate imbalance can occur for any specific randomization. As such, statistical adjustments for accidental imbalance are common with experimental data. The most common method of adjustment for accidental imbalance is to use least squares to estimate the analysis of covariance (ANCOVA) model. ANCOVA, however, is a poor choice for the adjustment of experimental data. It has a strong functional form assumption, and the least squares estimator is notably biased in sample sizes of less than 500 when applied to the analysis of treatment effects. We evaluate alternative methods of adjusting experimental data. We compare ANCOVA to two different techniques. The first technique is a modified version of ANCOVA that relaxes the strong functional form assumption of this model. The second technique is matching, and we test the differences between two matching methods. For the first, we match subjects and then randomize treatment across pairs. For the second, we randomize the treatment and match prior to the estimation of treatment effects. We use all three techniques with data from a series of experiments on racial priming. We find that matching substantially increases the efficiency of experimental designs.
Giving Order to Districts: Estimating Voter Distributions with National Election Returns
Kernell, Georgia
Submitted: 2008-07-07
Keywords: district ideology, voter distribution, election returns
Abstract: (click to show/hide) Correctly measuring district preferences is crucial for empirical research on legislative responsiveness and voting behavior. This article argues that the common practice of using presidential vote shares to measure congressional district ideology systematically produces incorrect estimates. I propose an alternative method that employs multiple election returns to estimate voters' ideological distributions within districts. I develop two estimation procedures -- a least squared error model and a Bayesian model -- and test each with simulations and empirical applications. The models are shown to outperform vote shares, and they are validated with direct measures of voter ideology and out of sample election predictions. Beyond estimating district ideology, these models provide valuable information on constituency heterogeneity, an important but understudied quality for understanding representatives' strategic behavior.
Kernell, Georgia
Submitted: 2008-07-07
Keywords: district ideology, voter distribution, election returns
Abstract: (click to show/hide) Correctly measuring district preferences is crucial for empirical research on legislative responsiveness and voting behavior. This article argues that the common practice of using presidential vote shares to measure congressional district ideology systematically produces incorrect estimates. I propose an alternative method that employs multiple election returns to estimate voters' ideological distributions within districts. I develop two estimation procedures -- a least squared error model and a Bayesian model -- and test each with simulations and empirical applications. The models are shown to outperform vote shares, and they are validated with direct measures of voter ideology and out of sample election predictions. Beyond estimating district ideology, these models provide valuable information on constituency heterogeneity, an important but understudied quality for understanding representatives' strategic behavior.
Registration and Voting under Rational Expectations
Achen, Christopher
Submitted: 2008-07-07
Keywords: turnout, registration, Heckman, Dubin-Rivers, expectations
Abstract: (click to show/hide) Alone among modern democracies, the United States makes voter registration a personal responsibility rather than a governmental function. In almost all states, registration deadlines occur well before elections. Failure to register by the deadline makes the probability of voting exactly zero. This sequential feature of the registration and voting decisions has been skipped over by most researchers, who simply ignore registration. Others, notably Timpone (1998), have used the seemingly appropriate Heckman-style selection model, but have arrived at findings difficult to believe. This paper investigates the appropriate choice of a registration model under a rational expectations assumption about the desire to vote, showing that, rather surprisingly, conventional selection models will generally perform less well than ignoring the selection effect of registration entirely. However, neither is quite correct. Finally then, the paper proposes and tests a flexible model for registration as a step toward substantively appropriate joint modeling of registration and voting.
Achen, Christopher
Submitted: 2008-07-07
Keywords: turnout, registration, Heckman, Dubin-Rivers, expectations
Abstract: (click to show/hide) Alone among modern democracies, the United States makes voter registration a personal responsibility rather than a governmental function. In almost all states, registration deadlines occur well before elections. Failure to register by the deadline makes the probability of voting exactly zero. This sequential feature of the registration and voting decisions has been skipped over by most researchers, who simply ignore registration. Others, notably Timpone (1998), have used the seemingly appropriate Heckman-style selection model, but have arrived at findings difficult to believe. This paper investigates the appropriate choice of a registration model under a rational expectations assumption about the desire to vote, showing that, rather surprisingly, conventional selection models will generally perform less well than ignoring the selection effect of registration entirely. However, neither is quite correct. Finally then, the paper proposes and tests a flexible model for registration as a step toward substantively appropriate joint modeling of registration and voting.
Voter transition estimation in multiparty systems
Andreadis, Ioannis
Submitted: 2008-07-07
Keywords: Elections, Voter transition rates, Ecological inference, Multiparty systems
Abstract: (click to show/hide) Recent advances in the field of ecological inference have provided researchers with new tools to estimate voter transition in two-party systems. Although some researchers have dealt with the R x C ecological inference problem, voter transition estimation remains a difficult and tedious goal. As a result scholars of multi-party systems still struggle with their electoral data. In this paper we present a new approach and we propose a new method that deals with this issue.
Andreadis, Ioannis
Submitted: 2008-07-07
Keywords: Elections, Voter transition rates, Ecological inference, Multiparty systems
Abstract: (click to show/hide) Recent advances in the field of ecological inference have provided researchers with new tools to estimate voter transition in two-party systems. Although some researchers have dealt with the R x C ecological inference problem, voter transition estimation remains a difficult and tedious goal. As a result scholars of multi-party systems still struggle with their electoral data. In this paper we present a new approach and we propose a new method that deals with this issue.
Research Opportunities - The 2009/10 British Election Study
Clarke, Harold, Sanders, David, Stewart, Marianne, Whiteley, Paul
Submitted: 2008-07-07
Keywords: electons, experiments, in-person, internet, public opinion
Abstract: (click to show/hide) The 2009/10 British Election Study (BES) will include significant research opportunities for students of voting, elections and public opinion. The BES will have three major components: (a) in-person pre-post election surveys; (b) rolling campaign internet panel survey (RCPS); (c) 48 inter-election monthly continuous monitoring surveys (CMS) with annual panel components. Each CMS survey will offer researchers opportunities to include question batteries including experiments. Participation is free and data release is very fast. Proposals for research modules reviewed by BES Advisory Board and P.I.s. Proposals also entertained for research modules on core and RCPS components.
Clarke, Harold, Sanders, David, Stewart, Marianne, Whiteley, Paul
Submitted: 2008-07-07
Keywords: electons, experiments, in-person, internet, public opinion
Abstract: (click to show/hide) The 2009/10 British Election Study (BES) will include significant research opportunities for students of voting, elections and public opinion. The BES will have three major components: (a) in-person pre-post election surveys; (b) rolling campaign internet panel survey (RCPS); (c) 48 inter-election monthly continuous monitoring surveys (CMS) with annual panel components. Each CMS survey will offer researchers opportunities to include question batteries including experiments. Participation is free and data release is very fast. Proposals for research modules reviewed by BES Advisory Board and P.I.s. Proposals also entertained for research modules on core and RCPS components.
The Trouble with Tobit: A District-Level Sample Selection Model of Voting for Extreme Right Parties in Europe, 1980-2004
Bowyer, Benjamin
Submitted: 2008-07-07
Keywords: Tobit, Heckman sample selection, censored data, aggregate data, extreme right parties
Abstract: (click to show/hide) The growing electoral success of extreme right parties (ERPs) in many European countries has sparked academic interest in explaining variation in extreme right success. However, much of the extant research on the electoral success of extreme right parties suffers from at least two types of selection bias. The first involves the selection of cases and occurs when only those national elections that were contested by extreme right parties are included in the cross-national analysis. To address this problem, a growing number of scholars of ERP electoral support employ Tobit models to analyze national-level election results pooled across countries and election years. However, this approach conceals a second source of selection bias: ERPs are extremely selective about which election districts within a country they choose to contest. The correct specification of this process of self-selection requires the recognition of two fundamental points. First, the causal factors that determine whether an extreme right party contests an election are not identical to those that influence its share of the vote if it does appear on the ballot. Second, this decision about when and where to field candidates is one that is observable at the level of the election district. This paper argues that the appropriate way to model is as a Heckman sample selection model estimated at the level of electoral district. I present a preliminary analysis of a dataset that pools district-level election results for eighteen European countries from 1980-2004 (N=12,050), the results of which demonstrate the value of this approach.
Bowyer, Benjamin
Submitted: 2008-07-07
Keywords: Tobit, Heckman sample selection, censored data, aggregate data, extreme right parties
Abstract: (click to show/hide) The growing electoral success of extreme right parties (ERPs) in many European countries has sparked academic interest in explaining variation in extreme right success. However, much of the extant research on the electoral success of extreme right parties suffers from at least two types of selection bias. The first involves the selection of cases and occurs when only those national elections that were contested by extreme right parties are included in the cross-national analysis. To address this problem, a growing number of scholars of ERP electoral support employ Tobit models to analyze national-level election results pooled across countries and election years. However, this approach conceals a second source of selection bias: ERPs are extremely selective about which election districts within a country they choose to contest. The correct specification of this process of self-selection requires the recognition of two fundamental points. First, the causal factors that determine whether an extreme right party contests an election are not identical to those that influence its share of the vote if it does appear on the ballot. Second, this decision about when and where to field candidates is one that is observable at the level of the election district. This paper argues that the appropriate way to model is as a Heckman sample selection model estimated at the level of electoral district. I present a preliminary analysis of a dataset that pools district-level election results for eighteen European countries from 1980-2004 (N=12,050), the results of which demonstrate the value of this approach.
The Strategic Interdependence of Foreign Aid: A Theoretically Informed Application of the Spatial Autoregressive Model
Steinwand, Martin
Submitted: 2008-07-07
Keywords: Spatial Autoregressive Model, Connectivity Matrix, Public Goods
Abstract: (click to show/hide) Spatial statistical methods in political science provide a tool to deal with spatial and other forms of interdependence in observational data. However, political scientist have been slow to use theory in conceptualizing how political units interconnect other than through geography. In this paper, I use a game theoretic impure public good model to derive the connectivity matrix for a spatial autoregressive (SAR) statistical model. I estimate two SAR models with pure respectively impure public good weights and compare their performance in summarizing data on international aid commitments from 1974 to 2006. I find some evidence for impure public good characteristics of aid during the cold war, and strong evidence for pure public good characteristics after the end of the cold war.
Steinwand, Martin
Submitted: 2008-07-07
Keywords: Spatial Autoregressive Model, Connectivity Matrix, Public Goods
Abstract: (click to show/hide) Spatial statistical methods in political science provide a tool to deal with spatial and other forms of interdependence in observational data. However, political scientist have been slow to use theory in conceptualizing how political units interconnect other than through geography. In this paper, I use a game theoretic impure public good model to derive the connectivity matrix for a spatial autoregressive (SAR) statistical model. I estimate two SAR models with pure respectively impure public good weights and compare their performance in summarizing data on international aid commitments from 1974 to 2006. I find some evidence for impure public good characteristics of aid during the cold war, and strong evidence for pure public good characteristics after the end of the cold war.
Problematic Choices: Testing for Correlated Unit Specific Effects in Panel Data
Troeger, Vera
Submitted: 2008-07-07
Keywords:
Abstract: (click to show/hide) The (generalized) Hausman specification test (Hausman 1978) is the gold-standard for political scientists using time-series cross-section data to check whether unit specific effects are correlated with right-hand-side variables. More than 500 articles (published in SSCI journals) over the last 20 years in Economics and Political Science used the Hausman test to justify the model choice, e.g. whether to employ a fixed effects or random effects/ pooled OLS specification. The asymptotic properties of the Hausman test and its variants are well known and formal power analyses have shown that the Hausman test performs reasonably well. Yet, the differences in the estimates of fixed effects and random effects models in finite samples can originate from two different sources: On the one hand, the Hausman test might rightly pick up differences that are caused by the inconsistency of the random effects estimator if unit specific effects are correlated with any of the explanatory variables and the random effects model therefore produces biased coefficients. On the other hand, differences might also stem from the inefficiency of the fixed effects estimator if explanatory variables are rarely changing and therefore only have a very small within variation. This inefficiency does not only lead to large standard errors but also to very unreliable point estimates that might be far away from the true relationship. While the Hausman test (and especially more recent variants and augmentations of the specification test) acknowledge the inefficiency of the fixed effects model and control for the differences in the asymptotic variances of the two estimators, this inefficiency in combination with correlated unit effects might still lead to unreliable test results. In International Relations and International and Comparative Political Economy where many of our explanatory variables measure institutions which do not change much over time this result might be especially harmful since the fixed effects model in this case produces very unreliable point estimates. This paper analyses the finite sample properties and power of the Hausman specification test by using Monte Carlo experiments. It shows under what conditions, e.g. the size of the correlation between unit specific effects and explanatory variables, and the between-within variance ratio of right-hand-side variables, the Hausman test generates misleading results.
Troeger, Vera
Submitted: 2008-07-07
Keywords:
Abstract: (click to show/hide) The (generalized) Hausman specification test (Hausman 1978) is the gold-standard for political scientists using time-series cross-section data to check whether unit specific effects are correlated with right-hand-side variables. More than 500 articles (published in SSCI journals) over the last 20 years in Economics and Political Science used the Hausman test to justify the model choice, e.g. whether to employ a fixed effects or random effects/ pooled OLS specification. The asymptotic properties of the Hausman test and its variants are well known and formal power analyses have shown that the Hausman test performs reasonably well. Yet, the differences in the estimates of fixed effects and random effects models in finite samples can originate from two different sources: On the one hand, the Hausman test might rightly pick up differences that are caused by the inconsistency of the random effects estimator if unit specific effects are correlated with any of the explanatory variables and the random effects model therefore produces biased coefficients. On the other hand, differences might also stem from the inefficiency of the fixed effects estimator if explanatory variables are rarely changing and therefore only have a very small within variation. This inefficiency does not only lead to large standard errors but also to very unreliable point estimates that might be far away from the true relationship. While the Hausman test (and especially more recent variants and augmentations of the specification test) acknowledge the inefficiency of the fixed effects model and control for the differences in the asymptotic variances of the two estimators, this inefficiency in combination with correlated unit effects might still lead to unreliable test results. In International Relations and International and Comparative Political Economy where many of our explanatory variables measure institutions which do not change much over time this result might be especially harmful since the fixed effects model in this case produces very unreliable point estimates. This paper analyses the finite sample properties and power of the Hausman specification test by using Monte Carlo experiments. It shows under what conditions, e.g. the size of the correlation between unit specific effects and explanatory variables, and the between-within variance ratio of right-hand-side variables, the Hausman test generates misleading results.
Ecological Inference with Covariates
Park, Won-ho
Submitted: 2008-07-08
Keywords: ecological inference, Thomsen, voter transition, South Korean, democratization
Abstract: (click to show/hide) The building block of ecological inference strategies is to construct a two-by-two table that describes the individual-level relationship from aggregate information. Extensions to this baseline model, whichever particular technique is employed, have been developed in the context of constructing bivariate R-by-C tables. However, another important and substantively interesting extension is a model that would let the researcher include additional covariates into the model and is yet to be fully discussed and developed. In the paper, I propose a method of moment estimator that incorporates covariates into the ecological inference process by extending Thomsen (1987)'s voter transition model. I apply the developed model to estimate the impact of demographic variables on turnout in South Korean voters over time, especially around democratization, using precinct-level electoral returns and census records.
Park, Won-ho
Submitted: 2008-07-08
Keywords: ecological inference, Thomsen, voter transition, South Korean, democratization
Abstract: (click to show/hide) The building block of ecological inference strategies is to construct a two-by-two table that describes the individual-level relationship from aggregate information. Extensions to this baseline model, whichever particular technique is employed, have been developed in the context of constructing bivariate R-by-C tables. However, another important and substantively interesting extension is a model that would let the researcher include additional covariates into the model and is yet to be fully discussed and developed. In the paper, I propose a method of moment estimator that incorporates covariates into the ecological inference process by extending Thomsen (1987)'s voter transition model. I apply the developed model to estimate the impact of demographic variables on turnout in South Korean voters over time, especially around democratization, using precinct-level electoral returns and census records.
Do Observational Methods Produce Reliable Results? The Use of Matching in Estimating the Treatment Effect of Class Size Reduction
Hosek, Adrienne
Submitted: 2008-07-09
Keywords:
Abstract: (click to show/hide) Several studies have tested the accuracy and validity of observational research methods to evaluate what estimation techniques . Randomized experiments are the gold standard of research design. When conducted correctly, such studies produce an unbiased estimate of the treatment effect for the experimental sample. Unfortunately, randomized experiments are rarely performed in the social sciences, largely due to insufficient resources. When a randomized experiment is not an option, social scientists turn to observational research methods to study the effects of a given treatment. Several previous studies have looked at the validity of using observational techniques to determine whether the reliably provide an accurate and consistent measure of a known treatment effect. In this paper, we re-eximine the work of Hollister and Wilde (2007), which did not systematically recover the experimental benchmark through propensity score analysis using data from an experimental study on class size reduction. They concluded that observational methods performed poorly based on these results. We find that they did not develop an appropriate test and thus the inability to achieve the experimental benchmark should not reflect flaws in the methodological approach, but rather stem from problems in test design.
Hosek, Adrienne
Submitted: 2008-07-09
Keywords:
Abstract: (click to show/hide) Several studies have tested the accuracy and validity of observational research methods to evaluate what estimation techniques . Randomized experiments are the gold standard of research design. When conducted correctly, such studies produce an unbiased estimate of the treatment effect for the experimental sample. Unfortunately, randomized experiments are rarely performed in the social sciences, largely due to insufficient resources. When a randomized experiment is not an option, social scientists turn to observational research methods to study the effects of a given treatment. Several previous studies have looked at the validity of using observational techniques to determine whether the reliably provide an accurate and consistent measure of a known treatment effect. In this paper, we re-eximine the work of Hollister and Wilde (2007), which did not systematically recover the experimental benchmark through propensity score analysis using data from an experimental study on class size reduction. They concluded that observational methods performed poorly based on these results. We find that they did not develop an appropriate test and thus the inability to achieve the experimental benchmark should not reflect flaws in the methodological approach, but rather stem from problems in test design.
Buying Votes with Public Funds in the US Presidential Election: Are Swing or Core Voters Easier to Buy Off?
Chen, Jowei
Submitted: 2008-07-09
Keywords: distributive politics, voting, turnout, elections
Abstract: (click to show/hide) In the aftermath of the summer 2004 Florida hurricane season, the Federal Emergency Management Agency (FEMA) distributed $1.2 billion in disaster aid among 2.6 million individual applications for assistance. This research measures the relative costs and benefits of using FEMA aid to buy votes from swing voters and core voters. First, I compare precinct-level vote counts and individual voter turnout records from the post-hurricane (November 2004) and pre-hurricane (2000 and 2002) elections to measure the effect of FEMA aid on Bush's vote share. Using a two-stage least squares estimator, with hurricane severity measures as instruments for FEMA aid, this analysis reveals that core Republican voters are most electorally responsive to FEMA aid -- $7,000 buys one additional vote for Bush. By contrast, in moderate precincts, each additional Bush vote costs $21,000, while voters in Democratic neighborhoods are unresponsive to receiving FEMA aid. Additionally, by tracking the geographic location of each aid recipient, the data reveal that FEMA favored applicants from Republican neighborhoods over those from Democratic or moderate neighborhoods, even conditioning on hurricane severity, average home values, and demographics. Collectively, these results demonstrate the Bush administration's disproportionate distribution of FEMA disaster aid toward core Republican areas was the optimal strategy for maximizing votes in the Presidential election.
Chen, Jowei
Submitted: 2008-07-09
Keywords: distributive politics, voting, turnout, elections
Abstract: (click to show/hide) In the aftermath of the summer 2004 Florida hurricane season, the Federal Emergency Management Agency (FEMA) distributed $1.2 billion in disaster aid among 2.6 million individual applications for assistance. This research measures the relative costs and benefits of using FEMA aid to buy votes from swing voters and core voters. First, I compare precinct-level vote counts and individual voter turnout records from the post-hurricane (November 2004) and pre-hurricane (2000 and 2002) elections to measure the effect of FEMA aid on Bush's vote share. Using a two-stage least squares estimator, with hurricane severity measures as instruments for FEMA aid, this analysis reveals that core Republican voters are most electorally responsive to FEMA aid -- $7,000 buys one additional vote for Bush. By contrast, in moderate precincts, each additional Bush vote costs $21,000, while voters in Democratic neighborhoods are unresponsive to receiving FEMA aid. Additionally, by tracking the geographic location of each aid recipient, the data reveal that FEMA favored applicants from Republican neighborhoods over those from Democratic or moderate neighborhoods, even conditioning on hurricane severity, average home values, and demographics. Collectively, these results demonstrate the Bush administration's disproportionate distribution of FEMA disaster aid toward core Republican areas was the optimal strategy for maximizing votes in the Presidential election.
Estimating Interdependent Duration Models with an Application to Government Formation and Survival
Hays, Jude, Kachi, Aya
Submitted: 2008-07-09
Keywords: Government Formation, Survival, Seemingly Unrelated Regressions, Simultaneous Equation Models, Weibull Distributions, Copulas
Abstract: (click to show/hide) This paper is part of a larger project in which we develop methods for estimating the causal effects of variables on (1) the duration of bargaining processes, broadly defined, and (2) the survival of bargained outcomes when both are jointly determined. There are many potential applications in political science including, but not limited to, the duration of war and survival of cease-fire agreements, coalition formation and government survival, and negotiations over and enforcement of international agreements. Our primary claim is that, in most cases, it is inappropriate to estimate the effects of variables on these two durations -- the bargaining and the outcome -- in isolation. Our argument is motivated by game theoretic models that show bargaining duration is correlated with the survival of bargained outcomes because players incorporate their beliefs about the survival of bargained outcomes into their decision-making at the bargaining stage. To address this problem, we develop, and examine the properties of two maximum likelihood estimators -- a seemingly unrelated regresssions (SUR) estimator and a limited information maximum likelihood (LIML) estimator. We use both estimators to analyze the duration of government formation and survival in a sample of European parliamentary democracies over the period 1945 to 1998. We conclude that estimated effects based on single equation models of either government formation or survival, the predominant method of analysis in the existing literature, are likely biased because they fail to capture significant indirect effects generated by strategic and other forms of interdependence that link the two durations.
Hays, Jude, Kachi, Aya
Submitted: 2008-07-09
Keywords: Government Formation, Survival, Seemingly Unrelated Regressions, Simultaneous Equation Models, Weibull Distributions, Copulas
Abstract: (click to show/hide) This paper is part of a larger project in which we develop methods for estimating the causal effects of variables on (1) the duration of bargaining processes, broadly defined, and (2) the survival of bargained outcomes when both are jointly determined. There are many potential applications in political science including, but not limited to, the duration of war and survival of cease-fire agreements, coalition formation and government survival, and negotiations over and enforcement of international agreements. Our primary claim is that, in most cases, it is inappropriate to estimate the effects of variables on these two durations -- the bargaining and the outcome -- in isolation. Our argument is motivated by game theoretic models that show bargaining duration is correlated with the survival of bargained outcomes because players incorporate their beliefs about the survival of bargained outcomes into their decision-making at the bargaining stage. To address this problem, we develop, and examine the properties of two maximum likelihood estimators -- a seemingly unrelated regresssions (SUR) estimator and a limited information maximum likelihood (LIML) estimator. We use both estimators to analyze the duration of government formation and survival in a sample of European parliamentary democracies over the period 1945 to 1998. We conclude that estimated effects based on single equation models of either government formation or survival, the predominant method of analysis in the existing literature, are likely biased because they fail to capture significant indirect effects generated by strategic and other forms of interdependence that link the two durations.
"The Size and Scope of International Unions: A Coalition-Theoretic Approach"
Konstantinidis, Nikitas
Submitted: 2008-07-10
Keywords: international unions; coalition theory; size and scope; flexible integration
Abstract: (click to show/hide) This paper examines the endogenous strategic considerations in simultaneously creating, enlarging, and deepening an international union of countries within a framework of variable geometry. We introduce a coalition-theoretic model to examine the equilibrium relationship between union size and scope. What is the equilibrium (stable) size and scope of an international union and how do these variables interact? When should we expect countries to take advantage of more flexible modes of integration and how does that possibility affect the pace and depth of integration? In tackling these questions, we characterize the various policy areas of cooperation with respect to their cross-country and cross-policy spillovers, their efficiency scales, the heterogeneity of preferences, and the general cost structure. We then go on to show that the enlargement of a union and the widening of its policy scope are too symbiotic and mutually reinforcing dynamic processes under certain conditions. This is an exciting research puzzle given that current game-theoretic predictions have been at odds with the empirical reality of European integration.
Konstantinidis, Nikitas
Submitted: 2008-07-10
Keywords: international unions; coalition theory; size and scope; flexible integration
Abstract: (click to show/hide) This paper examines the endogenous strategic considerations in simultaneously creating, enlarging, and deepening an international union of countries within a framework of variable geometry. We introduce a coalition-theoretic model to examine the equilibrium relationship between union size and scope. What is the equilibrium (stable) size and scope of an international union and how do these variables interact? When should we expect countries to take advantage of more flexible modes of integration and how does that possibility affect the pace and depth of integration? In tackling these questions, we characterize the various policy areas of cooperation with respect to their cross-country and cross-policy spillovers, their efficiency scales, the heterogeneity of preferences, and the general cost structure. We then go on to show that the enlargement of a union and the widening of its policy scope are too symbiotic and mutually reinforcing dynamic processes under certain conditions. This is an exciting research puzzle given that current game-theoretic predictions have been at odds with the empirical reality of European integration.
Bayesian Estimates of Party Left-Right Scores
Albright, Jeremy
Submitted: 2008-07-11
Keywords:
Abstract: (click to show/hide) Spatial imagery is ubiquitous in political science, yet comparativists disagree about the best way to determine where actors are located on latent issue dimensions such as the left-right scale. Although different methods have been proposed, each has its own limitations. Scores derived from the Comparative Manifestos Project (CMP) are almost always presented without confidence intervals, expert surveys do not vary over time, and text-based analyses are limited by the availability of relevant documents. This paper argues that Bayesian simulation can be used with CMP data to produce valid left-right scores in a manner that offers important improvements over alternatives: 1) estimates are accompanied by measures of uncertainty; 2) prior information such as from expert surveys can be incorporated into the estimation, and 3) the statistical model has a stronger theoretical basis that generalizes to very different settings, such as the analysis of roll call votes in the American Congress.
Albright, Jeremy
Submitted: 2008-07-11
Keywords:
Abstract: (click to show/hide) Spatial imagery is ubiquitous in political science, yet comparativists disagree about the best way to determine where actors are located on latent issue dimensions such as the left-right scale. Although different methods have been proposed, each has its own limitations. Scores derived from the Comparative Manifestos Project (CMP) are almost always presented without confidence intervals, expert surveys do not vary over time, and text-based analyses are limited by the availability of relevant documents. This paper argues that Bayesian simulation can be used with CMP data to produce valid left-right scores in a manner that offers important improvements over alternatives: 1) estimates are accompanied by measures of uncertainty; 2) prior information such as from expert surveys can be incorporated into the estimation, and 3) the statistical model has a stronger theoretical basis that generalizes to very different settings, such as the analysis of roll call votes in the American Congress.
Is Matching Really Essential?
Middleton, Joel
Submitted: 2008-07-11
Keywords:
Abstract: (click to show/hide) Conference poster
Middleton, Joel
Submitted: 2008-07-11
Keywords:
Abstract: (click to show/hide) Conference poster
Learning from the Campaign Context: Multivariate Matching with Exposure
Christenson, Dino
Submitted: 2008-07-14
Keywords: multivariate matching, non-bipartite matching, signed rank test, sensitivity analysis, political information, presidential campaigns
Abstract: (click to show/hide) PolMeth XXV poster.
Christenson, Dino
Submitted: 2008-07-14
Keywords: multivariate matching, non-bipartite matching, signed rank test, sensitivity analysis, political information, presidential campaigns
Abstract: (click to show/hide) PolMeth XXV poster.
Investigate at extreme right : Between total immersion and participant observations, the example of French National Front (2006-2008)
Mermat, Djamel
Submitted: 2008-07-18
Keywords: France, Far right, electoral campaigns, Methodology, Immersion, Participant observation, Political party.
Abstract: (click to show/hide) There is a particular situation involving the NF that has been noticeably neglected to date in France: the capture live of the motivations and actions of these new partisans who rallied to the movement during the last three years (Glenn, 2005: 35-43). We must also recognize that enabling us to understand this party in "campaigning mode," there is insufficient knowledge. Nonetheless, if we hope to remedy these basic two weaknesses, what methods could researchers employ? Consequently, what can political science methodology eventually learn from an adjustment in the status of the researcher on the ground and at the time of the inquiry? More precisely: what advantages do participant observation employed almost daily offer? What are the basic contributions of total immersion in the "Frontist" environment? Given these questions, we wanted, based on comparative qualitative research, to explain what fund the validity of the results obtained (Kent, 2001), through establishing a cost-benefit analysis of the use of two different methods, of two inherently quite distinct presentations. Indeed, the result very rarely mentions the researcher's many ups and downs. However, the successes and inevitable failures of the ethnographic investigation condition the nature of the data collected. Therefore, this is an attempt to address several methodological deficiencies or silences, and to reverse certain epistemological biases, through returning to concepts whose substance needs clarification: "participant observation," "empathy," "total immersion," and "infiltration." All the underpinnings of the research do, however, draw attention to the manner in which the political analyst created his methodology and analytical categories, as well as his own approach to the subject under study. As a result, at first we will emphasize the difference in scale between our two research fields, since it led to our adoption of another approach to the subject (I). Thus, we first chose as our research location the North Flanders Federation from June 2006 to the start of November 2007, the beginning of the presidential campaign, up to the presentation of the assessment of the local councillors. Still, from the month of June 2007, and without abandoning our initial site, we progressively accorded increasing attention to the "new partisans" supporting Marine Le Pen and Steeve Briois in the 14th constituency of Pas-de-Calais, in particular in the city of Henin-Beaumont. In the first week of December 2007, this led us to commence our exploration of the diversity of actors of the General Headquarters of the "Henin-Beaumont pour Vous" list campaign. Henin-Beaumont belongs to the Federation of Mayors of Mid-Sized Cities. Well, to date, no study on the NF has been interested in its "propaganda" strategy (Kalinowski, 2005) for a mid-sized city and during an election campaign, even less for a municipal. The idea was to slide, over a period of several weeks from Flanders to Pas-de-Calais, from the status of participant observer outside of the group, to that of active member at the periphery of the central group, thus, integrated in the group (Strauss, Corbin, and Soulet, 2004). This process offered the researcher the opportunity to situate himself somewhere between simply "taking part" and being "uncovered." Thus, the necessity of reacting, at the spur of the moment, when confronted with the unexpected (II), was the most challenging aspect. Moreover, it is this absence, of a recent localized investigation through direct observation over an extended period, of a political enterprise still provoking concerns and anathemas that propelled us to study what the FN electoral campaigns do to the researcher and his analytical tools.
Mermat, Djamel
Submitted: 2008-07-18
Keywords: France, Far right, electoral campaigns, Methodology, Immersion, Participant observation, Political party.
Abstract: (click to show/hide) There is a particular situation involving the NF that has been noticeably neglected to date in France: the capture live of the motivations and actions of these new partisans who rallied to the movement during the last three years (Glenn, 2005: 35-43). We must also recognize that enabling us to understand this party in "campaigning mode," there is insufficient knowledge. Nonetheless, if we hope to remedy these basic two weaknesses, what methods could researchers employ? Consequently, what can political science methodology eventually learn from an adjustment in the status of the researcher on the ground and at the time of the inquiry? More precisely: what advantages do participant observation employed almost daily offer? What are the basic contributions of total immersion in the "Frontist" environment? Given these questions, we wanted, based on comparative qualitative research, to explain what fund the validity of the results obtained (Kent, 2001), through establishing a cost-benefit analysis of the use of two different methods, of two inherently quite distinct presentations. Indeed, the result very rarely mentions the researcher's many ups and downs. However, the successes and inevitable failures of the ethnographic investigation condition the nature of the data collected. Therefore, this is an attempt to address several methodological deficiencies or silences, and to reverse certain epistemological biases, through returning to concepts whose substance needs clarification: "participant observation," "empathy," "total immersion," and "infiltration." All the underpinnings of the research do, however, draw attention to the manner in which the political analyst created his methodology and analytical categories, as well as his own approach to the subject under study. As a result, at first we will emphasize the difference in scale between our two research fields, since it led to our adoption of another approach to the subject (I). Thus, we first chose as our research location the North Flanders Federation from June 2006 to the start of November 2007, the beginning of the presidential campaign, up to the presentation of the assessment of the local councillors. Still, from the month of June 2007, and without abandoning our initial site, we progressively accorded increasing attention to the "new partisans" supporting Marine Le Pen and Steeve Briois in the 14th constituency of Pas-de-Calais, in particular in the city of Henin-Beaumont. In the first week of December 2007, this led us to commence our exploration of the diversity of actors of the General Headquarters of the "Henin-Beaumont pour Vous" list campaign. Henin-Beaumont belongs to the Federation of Mayors of Mid-Sized Cities. Well, to date, no study on the NF has been interested in its "propaganda" strategy (Kalinowski, 2005) for a mid-sized city and during an election campaign, even less for a municipal. The idea was to slide, over a period of several weeks from Flanders to Pas-de-Calais, from the status of participant observer outside of the group, to that of active member at the periphery of the central group, thus, integrated in the group (Strauss, Corbin, and Soulet, 2004). This process offered the researcher the opportunity to situate himself somewhere between simply "taking part" and being "uncovered." Thus, the necessity of reacting, at the spur of the moment, when confronted with the unexpected (II), was the most challenging aspect. Moreover, it is this absence, of a recent localized investigation through direct observation over an extended period, of a political enterprise still provoking concerns and anathemas that propelled us to study what the FN electoral campaigns do to the researcher and his analytical tools.
The Persuasive Effects of Direct Mail: A Regression Discontinuity Approach
Meredith, Marc, Kessler, Daniel, Gerber, Alan
Submitted: 2008-07-21
Keywords: regression discontinuity, direct mail, persuasion, turnout
Abstract: (click to show/hide) During the contest for Kansas attorney general in 2006, an organization sent out 6 pieces of mail criticizing the incumbent's conduct in office. We exploit a discontinuity in the rule used to select which households received the mailings to identify the causal effect of mail on vote choice and voter turnout. We find these mailings had both a statistically and politically significant effect on the challenger's vote share. Our estimates suggest that a ten percentage point increase in the amount of mail sent to a precinct increased the challenger's vote share by approximately three percentage points. Furthermore, our results suggest that the mechanism for this increase was persuasion rather than mobilization.
Meredith, Marc, Kessler, Daniel, Gerber, Alan
Submitted: 2008-07-21
Keywords: regression discontinuity, direct mail, persuasion, turnout
Abstract: (click to show/hide) During the contest for Kansas attorney general in 2006, an organization sent out 6 pieces of mail criticizing the incumbent's conduct in office. We exploit a discontinuity in the rule used to select which households received the mailings to identify the causal effect of mail on vote choice and voter turnout. We find these mailings had both a statistically and politically significant effect on the challenger's vote share. Our estimates suggest that a ten percentage point increase in the amount of mail sent to a precinct increased the challenger's vote share by approximately three percentage points. Furthermore, our results suggest that the mechanism for this increase was persuasion rather than mobilization.
Exploiting a Rare Shift in Communication Flows to Document News Media Persuasion: The 1997 United Kingdom General Election
Ladd, Jonathan, Lenz, Gabriel
Submitted: 2008-07-30
Keywords: Media persuasion, endorsements, campaigns, elections, matching, causal inference
Abstract: (click to show/hide) Using panel data and matching techniques, we exploit a rare change in communication flows -- the endorsement switch to the Labour Party by several prominent British newspapers before the 1997 United Kingdom general election -- to study the persuasive power of the news media. These unusual events provide an opportunity to test for news media persuasion while avoiding methodological pitfalls that have plagued previous studies. By comparing readers of newspapers that switched endorsements to similar individuals who did not read these newspapers, we estimate that these papers persuaded a considerable share of their readers to vote for Labour. Depending on the statistical approach, the point estimates vary from about 10 percent to as high as 25 percent of readers. These findings provide rare, compelling evidence that the news media exert a powerful influence on mass political behavior.
Ladd, Jonathan, Lenz, Gabriel
Submitted: 2008-07-30
Keywords: Media persuasion, endorsements, campaigns, elections, matching, causal inference
Abstract: (click to show/hide) Using panel data and matching techniques, we exploit a rare change in communication flows -- the endorsement switch to the Labour Party by several prominent British newspapers before the 1997 United Kingdom general election -- to study the persuasive power of the news media. These unusual events provide an opportunity to test for news media persuasion while avoiding methodological pitfalls that have plagued previous studies. By comparing readers of newspapers that switched endorsements to similar individuals who did not read these newspapers, we estimate that these papers persuaded a considerable share of their readers to vote for Labour. Depending on the statistical approach, the point estimates vary from about 10 percent to as high as 25 percent of readers. These findings provide rare, compelling evidence that the news media exert a powerful influence on mass political behavior.
Nonparametric Priors For Ordinal Bayesian Social Science Models: Specification and Estimation
Gill, Jeff, Casella, George
Submitted: 2008-08-21
Keywords: generalized linear mixed model, ordered probit, Bayesian approaches, nonparametric priors, Dirichlet process mixture models, nonparametric Bayesian inference
Abstract: (click to show/hide) A generalized linear mixed model, ordered probit, is used to estimate levels of stress in presidential political appointees as a means of understanding their surprisingly short tenures. A Bayesian approach is developed, where the random effects are modeled with a Dirichlet process mixture prior, allowing for useful incorporation of prior information, but retaining some vagueness in the form of the prior. Applications of Bayesian models in the social sciences are typically done with ``noninformative'' priors, although some use of informed versions exists. There has been disagreement over this, and our approach may be a step in the direction of satisfying both camps. We give a detailed description of the data, show how to implement the model, and describe some interesting conclusions. The model utilizing a nonparametric prior fits better and reveals more information in the data than standard approaches.
Gill, Jeff, Casella, George
Submitted: 2008-08-21
Keywords: generalized linear mixed model, ordered probit, Bayesian approaches, nonparametric priors, Dirichlet process mixture models, nonparametric Bayesian inference
Abstract: (click to show/hide) A generalized linear mixed model, ordered probit, is used to estimate levels of stress in presidential political appointees as a means of understanding their surprisingly short tenures. A Bayesian approach is developed, where the random effects are modeled with a Dirichlet process mixture prior, allowing for useful incorporation of prior information, but retaining some vagueness in the form of the prior. Applications of Bayesian models in the social sciences are typically done with ``noninformative'' priors, although some use of informed versions exists. There has been disagreement over this, and our approach may be a step in the direction of satisfying both camps. We give a detailed description of the data, show how to implement the model, and describe some interesting conclusions. The model utilizing a nonparametric prior fits better and reveals more information in the data than standard approaches.
Public Opinion and Senate Confirmation of Supreme Court Nominees
Kastellec, Jonathan, Lax, Jeffrey, Phillips, Justin
Submitted: 2008-08-22
Keywords: Supreme Court, nominations, public opinion, multilevel models, poststratification,
Abstract: (click to show/hide) We study the relationship between state-level public opinion and the roll call votes of senators on Supreme Court nominees. Applying recent advances in multilevel modeling, we use national polls on nine recent Supreme Court nominees to produce state-of-the-art estimates of public support for the confirmation of each nominee in all 50 states. We show that greater public support strongly increases the probability that a senator will vote to approve a nominee, even after controlling for standard predictors of roll call voting. We also find that the impact of opinion varies with context: it has a greater effect on opposition party senators, on ideologically opposed senators, and for generally weak nominees. These results establish a systematic and powerful link between constituency opinion and voting on Supreme Court nominees.
Kastellec, Jonathan, Lax, Jeffrey, Phillips, Justin
Submitted: 2008-08-22
Keywords: Supreme Court, nominations, public opinion, multilevel models, poststratification,
Abstract: (click to show/hide) We study the relationship between state-level public opinion and the roll call votes of senators on Supreme Court nominees. Applying recent advances in multilevel modeling, we use national polls on nine recent Supreme Court nominees to produce state-of-the-art estimates of public support for the confirmation of each nominee in all 50 states. We show that greater public support strongly increases the probability that a senator will vote to approve a nominee, even after controlling for standard predictors of roll call voting. We also find that the impact of opinion varies with context: it has a greater effect on opposition party senators, on ideologically opposed senators, and for generally weak nominees. These results establish a systematic and powerful link between constituency opinion and voting on Supreme Court nominees.
Survey Context Effects in Anchoring Vignettes
Buckley, Jack
Submitted: 2008-08-22
Keywords: anchoring vignettes, survey research, differential item functioning, experiment
Abstract: (click to show/hide) Methodologists (King et al. 2004; King and Wand 2007) have recently proposed a novel approach to adjusting for bias in interpersonal and cross- cultural comparisons in survey research. The method centers on the use of anchoring vignettes to allow the statistical correction of differential usage of ordinal response scales at the individual or group level. Using data from a randomized survey experiment I investigate whether analyses based on these vignettes may be vulnerable to the introduction of survey artifacts due to vignette ordering or the placement of the self-assessment item relative to the vignettes. I find several patterns of bias due to context effects. Researchers using anchoring vignettes should consider randomization or other methods to mitigate these problems.
Buckley, Jack
Submitted: 2008-08-22
Keywords: anchoring vignettes, survey research, differential item functioning, experiment
Abstract: (click to show/hide) Methodologists (King et al. 2004; King and Wand 2007) have recently proposed a novel approach to adjusting for bias in interpersonal and cross- cultural comparisons in survey research. The method centers on the use of anchoring vignettes to allow the statistical correction of differential usage of ordinal response scales at the individual or group level. Using data from a randomized survey experiment I investigate whether analyses based on these vignettes may be vulnerable to the introduction of survey artifacts due to vignette ordering or the placement of the self-assessment item relative to the vignettes. I find several patterns of bias due to context effects. Researchers using anchoring vignettes should consider randomization or other methods to mitigate these problems.
Circular Data in Political Science and How to Handle It
Gill, Jeff, Hangartner, Dominik
Submitted: 2008-08-25
Keywords: circular data, von Mises distribution, clock and calendar effects, directional data, radial measures, Iraq casualties, party movement model
Abstract: (click to show/hide) There has been no attention to circular (purely cyclical) data in political science research. We show that such data exists and is generally mishandled by models that do not take into account the inherently recycling nature of some phenomenon. Clock and calendar effects are the obvious cases, but directional data exists as well. We develop a modeling framework based on the von Mises distribution and apply it to two datasets: casualties in the second Iraq war and party movement in a two-dimensional ideological space. Results clearly demonstrate the importance of circular regression models to handle periodic and directional data.
Gill, Jeff, Hangartner, Dominik
Submitted: 2008-08-25
Keywords: circular data, von Mises distribution, clock and calendar effects, directional data, radial measures, Iraq casualties, party movement model
Abstract: (click to show/hide) There has been no attention to circular (purely cyclical) data in political science research. We show that such data exists and is generally mishandled by models that do not take into account the inherently recycling nature of some phenomenon. Clock and calendar effects are the obvious cases, but directional data exists as well. We develop a modeling framework based on the von Mises distribution and apply it to two datasets: casualties in the second Iraq war and party movement in a two-dimensional ideological space. Results clearly demonstrate the importance of circular regression models to handle periodic and directional data.
Rebels with a Cause? Legislative Activity and the Personal Vote in Britain, 1997--2005
Spirling, Arthur
Submitted: 2008-08-28
Keywords: Westminster Systems, Accountability, Representation, Random Forests
Abstract: (click to show/hide) Does a Member of the British Parliament's voting record have any effect on their constituency electoral performance? Scholars have assumed not, else they have tested the proposition with an extremely limited number of roll calls. Congruent with public opinion findings we contend that, paradoxically, voters conditionally reward both 'party unity' and 'independent mindedness' in their elected representatives. Using novel non-parametric `random forest' classification procedures, and a new data set recording behavior on over 2000 roll calls from 1997-2001 and 2001-2005, along with commensurate constituency controls, we thus show that MPs' popularity is indeed affected by their legislative activity in small but significant ways. In particular, government-party voters demand unity on votes that are key parts of the government's programmatic agenda, while welcoming more 'maverick' behavior on less important issues.
Spirling, Arthur
Submitted: 2008-08-28
Keywords: Westminster Systems, Accountability, Representation, Random Forests
Abstract: (click to show/hide) Does a Member of the British Parliament's voting record have any effect on their constituency electoral performance? Scholars have assumed not, else they have tested the proposition with an extremely limited number of roll calls. Congruent with public opinion findings we contend that, paradoxically, voters conditionally reward both 'party unity' and 'independent mindedness' in their elected representatives. Using novel non-parametric `random forest' classification procedures, and a new data set recording behavior on over 2000 roll calls from 1997-2001 and 2001-2005, along with commensurate constituency controls, we thus show that MPs' popularity is indeed affected by their legislative activity in small but significant ways. In particular, government-party voters demand unity on votes that are key parts of the government's programmatic agenda, while welcoming more 'maverick' behavior on less important issues.
Noughts and Crosses. Challenges in Generating Political Positions from CMP-Data.
Hans, Silke, Hoennige, Christoph
Submitted: 2008-08-29
Keywords: Comparative Politics, Manifesto Data, Party Positions
Abstract: (click to show/hide) The Comparative Manifesto Project (CMP) dataset is the only dataset providing information about the positions of parties for comparative researchers across time and countries. This article evaluates its structure and finds a peculiarity: A high number of zeros and their unequal distribution across items, countries and time. They influence the results of any procedure to build a scale, but especially those using factor analyses. The article shows that zeroes have different meanings: Firstly, there are substantial zeroes in line with saliency theory. Secondly, zeroes exist for non-substantial reasons: The length of a manifesto and the percentage of uncoded sentences, both strongly varying across time and country. We quantify the problem and propose a procedure to identify data points containing non-substantial zeroes. For the future comparative use of the dataset we plead for a theoretical selection of items combined with the information about the likelihood that zeroes are substantially meaningful.
Hans, Silke, Hoennige, Christoph
Submitted: 2008-08-29
Keywords: Comparative Politics, Manifesto Data, Party Positions
Abstract: (click to show/hide) The Comparative Manifesto Project (CMP) dataset is the only dataset providing information about the positions of parties for comparative researchers across time and countries. This article evaluates its structure and finds a peculiarity: A high number of zeros and their unequal distribution across items, countries and time. They influence the results of any procedure to build a scale, but especially those using factor analyses. The article shows that zeroes have different meanings: Firstly, there are substantial zeroes in line with saliency theory. Secondly, zeroes exist for non-substantial reasons: The length of a manifesto and the percentage of uncoded sentences, both strongly varying across time and country. We quantify the problem and propose a procedure to identify data points containing non-substantial zeroes. For the future comparative use of the dataset we plead for a theoretical selection of items combined with the information about the likelihood that zeroes are substantially meaningful.
What Can Be Learned from a Simple Table? Bayesian Inference and Sensitivity Analysis for Causal Effects from 2x2 and 2x2xK Tables in the Presence of Unmeasured Confounding
Quinn, Kevin
Submitted: 2008-09-07
Keywords: causal inference, bayesian inference, sensitivity analysis, unmeasured confounding
Abstract: (click to show/hide) What, if anything, should one infer about the causal effect of a binary treatment on a binary outcome from a $2 \times 2$ cross-tabulation of non-experimental data? Many researchers would answer ``nothing'' because of the likelihood of severe bias due to the lack of adjustment for key confounding variables. This paper shows that such a conclusion is unduly pessimistic. Because the complete data likelihood under arbitrary patterns of confounding factorizes in a particularly convenient way, it is possible to parameterize this general situation with four easily interpretable parameters. Subjective beliefs regarding these parameters are easily elicited and subjective statements of uncertainty become possible. This paper also develops a novel graphical display called the confounding plot that quickly and efficiently communicates all patterns of confounding that would leave a particular causal inference relatively unchanged.
Quinn, Kevin
Submitted: 2008-09-07
Keywords: causal inference, bayesian inference, sensitivity analysis, unmeasured confounding
Abstract: (click to show/hide) What, if anything, should one infer about the causal effect of a binary treatment on a binary outcome from a $2 \times 2$ cross-tabulation of non-experimental data? Many researchers would answer ``nothing'' because of the likelihood of severe bias due to the lack of adjustment for key confounding variables. This paper shows that such a conclusion is unduly pessimistic. Because the complete data likelihood under arbitrary patterns of confounding factorizes in a particularly convenient way, it is possible to parameterize this general situation with four easily interpretable parameters. Subjective beliefs regarding these parameters are easily elicited and subjective statements of uncertainty become possible. This paper also develops a novel graphical display called the confounding plot that quickly and efficiently communicates all patterns of confounding that would leave a particular causal inference relatively unchanged.
Cosponsorship in the U.S. Senate: A Multilevel Approach to Detecting Subtle Social Predictors of Legilslative Support
Gross, Justin
Submitted: 2008-09-14
Keywords: Congress, cosponsorship, social network analysis, multilevel models, mixed effects, GLMM
Abstract: (click to show/hide) Why do members of Congress choose to cosponsor legislation proposed by their colleagues and what can we learn from their patterns of cosponsorship? To answer these questions properly requires models that respect the relational nature of the relevant data and the resulting interdependence among observations. We show how the inclusion of carefully selected random effects can capture network-type dependence, allowing us to more confidently investigate senators' propensity to support colleagues' proposals. To illustrate, we examine whether certain social factors such as demographic similarities, opportunities for interaction, and institutional roles are associated with varying odds of cosponsorship during the 2003-04 (108th) Senate.
Gross, Justin
Submitted: 2008-09-14
Keywords: Congress, cosponsorship, social network analysis, multilevel models, mixed effects, GLMM
Abstract: (click to show/hide) Why do members of Congress choose to cosponsor legislation proposed by their colleagues and what can we learn from their patterns of cosponsorship? To answer these questions properly requires models that respect the relational nature of the relevant data and the resulting interdependence among observations. We show how the inclusion of carefully selected random effects can capture network-type dependence, allowing us to more confidently investigate senators' propensity to support colleagues' proposals. To illustrate, we examine whether certain social factors such as demographic similarities, opportunities for interaction, and institutional roles are associated with varying odds of cosponsorship during the 2003-04 (108th) Senate.
Just Plain Data Analysis: Common Statistical Fallacies in Analyses of Social Indicator Data
Klass, Gary
Submitted: 2008-09-17
Keywords: Teaching, statistical fallacies, social indicators
Abstract: (click to show/hide) This paper presents a short summary of the most common statistical fallacies found in public debates employing social indicator data as the evidentiary premises of arguments about politics and public affairs. The purpose is to offer students a convenient framework for evaluating, and developing the own, arguments relying on social indicator data.
Klass, Gary
Submitted: 2008-09-17
Keywords: Teaching, statistical fallacies, social indicators
Abstract: (click to show/hide) This paper presents a short summary of the most common statistical fallacies found in public debates employing social indicator data as the evidentiary premises of arguments about politics and public affairs. The purpose is to offer students a convenient framework for evaluating, and developing the own, arguments relying on social indicator data.
Bayesian Combination of State Polls and Election Forecasts
Lock, Kari, Gelman, Andrew
Submitted: 2008-09-21
Keywords: election prediction, pre-election polls, Bayesian updating, shrinkage estimation
Abstract: (click to show/hide) In February of 2008, SurveyUSA polled 600 people in each state and asked who they would vote for in either head-to-head match-up: Obama vs. McCain, and Clinton vs. McCain. Here we integrate these polls with prior information; how each state voted in comparison to the national outcome in the 2004 election. We use Bayesian methods to merge prior and poll data, weighting each by its respective information. The variance for our poll data incorporates both sampling variability and variability due to time before the election, estimated using pre-election poll data from the 2000 and 2004 elections. The variance for our prior data is estimated using the results of the past nine presidential elections. The union of prior and poll data results in a posterior distribution predicting how each state will vote, in turn giving us posterior intervals for both the popular and electoral vote outcomes of the 2008 presidential election. Lastly, these posterior distributions are updated with the most recent poll data as of August, 2008.
Lock, Kari, Gelman, Andrew
Submitted: 2008-09-21
Keywords: election prediction, pre-election polls, Bayesian updating, shrinkage estimation
Abstract: (click to show/hide) In February of 2008, SurveyUSA polled 600 people in each state and asked who they would vote for in either head-to-head match-up: Obama vs. McCain, and Clinton vs. McCain. Here we integrate these polls with prior information; how each state voted in comparison to the national outcome in the 2004 election. We use Bayesian methods to merge prior and poll data, weighting each by its respective information. The variance for our poll data incorporates both sampling variability and variability due to time before the election, estimated using pre-election poll data from the 2000 and 2004 elections. The variance for our prior data is estimated using the results of the past nine presidential elections. The union of prior and poll data results in a posterior distribution predicting how each state will vote, in turn giving us posterior intervals for both the popular and electoral vote outcomes of the 2008 presidential election. Lastly, these posterior distributions are updated with the most recent poll data as of August, 2008.
Design, Inference, and the Strategic Logic of Suicide Terrorism: A Rejoinder
Clinton, Joshua, Ashworth, Scott, Ramsay, Kris, Meirowitz, Adam
Submitted: 2008-09-25
Keywords: Research Design, Terrorism
Abstract: (click to show/hide) In "Design, Inference, and the Strategic Logic of Suicide Terrorism", we show that Robert Pape�s work on suicide terrorism, particularly his 2003 American Political Science Review article, is deeply flawed. In "Methods and Findings in the Study of Suicide Terrorism" (2008), Pape claims that our criticisms of his work are incorrect. The bulk of his response, however, ignores the problem we identify in our comment; instead, he largely summarizes arguments from his later work, arguments that are irrelevant to our basic point. And when he eventually addresses the substance of our critique, Pape simply repeats the error that motivated our original comment.
Clinton, Joshua, Ashworth, Scott, Ramsay, Kris, Meirowitz, Adam
Submitted: 2008-09-25
Keywords: Research Design, Terrorism
Abstract: (click to show/hide) In "Design, Inference, and the Strategic Logic of Suicide Terrorism", we show that Robert Pape�s work on suicide terrorism, particularly his 2003 American Political Science Review article, is deeply flawed. In "Methods and Findings in the Study of Suicide Terrorism" (2008), Pape claims that our criticisms of his work are incorrect. The bulk of his response, however, ignores the problem we identify in our comment; instead, he largely summarizes arguments from his later work, arguments that are irrelevant to our basic point. And when he eventually addresses the substance of our critique, Pape simply repeats the error that motivated our original comment.
Beyond "Fixed Versus Random Effects": A Framework for Improving Substantive and Statistical Analysis of Panel, TSCS, and Multilevel Data
Bartels, Brandon
Submitted: 2008-09-30
Keywords: random effects, fixed effects, pooling, time-series cross-sectional data, panel data, multilevel modeling
Abstract: (click to show/hide) Researchers analyzing panel, time-series cross-sectional, and multilevel data often choose between a random effects, fixed effects, or complete pooling modeling approach. While pros and cons exist for each approach, I contend that some core issues concerning clustered data continue to be ignored. I present a unified and simple modeling framework for analyzing clustered data that solves many of the substantive and statistical problems inherent in extant approaches. The approach: (1) solves the substantive interpretation problems associated with cluster confounding, which occurs when one assumes that within- and between-cluster effects are equal; (2) accounts for cluster-level unobserved heterogeneity via a random intercept model; (3) satisfies the controversial statistical assumption that level-1 variables be uncorrelated with the random effects term; (4) allows for the inclusion of level-2 variables; and (5) allows for statistical tests of cluster confounding. I illustrate this approach using three substantive examples: global human rights abuse, oil production for OPEC countries, and Senate voting on Supreme Court nominations. Reexaminations of these data produce refined interpretations of some of the core substantive conclusions.
Bartels, Brandon
Submitted: 2008-09-30
Keywords: random effects, fixed effects, pooling, time-series cross-sectional data, panel data, multilevel modeling
Abstract: (click to show/hide) Researchers analyzing panel, time-series cross-sectional, and multilevel data often choose between a random effects, fixed effects, or complete pooling modeling approach. While pros and cons exist for each approach, I contend that some core issues concerning clustered data continue to be ignored. I present a unified and simple modeling framework for analyzing clustered data that solves many of the substantive and statistical problems inherent in extant approaches. The approach: (1) solves the substantive interpretation problems associated with cluster confounding, which occurs when one assumes that within- and between-cluster effects are equal; (2) accounts for cluster-level unobserved heterogeneity via a random intercept model; (3) satisfies the controversial statistical assumption that level-1 variables be uncorrelated with the random effects term; (4) allows for the inclusion of level-2 variables; and (5) allows for statistical tests of cluster confounding. I illustrate this approach using three substantive examples: global human rights abuse, oil production for OPEC countries, and Senate voting on Supreme Court nominations. Reexaminations of these data produce refined interpretations of some of the core substantive conclusions.
Can October Surprise? A Natural Experiment Assessing Late Campaign Effects
Meredith, Marc, Malhotra, Neil
Submitted: 2008-10-14
Keywords: Vote by mail, natural experiment, campaign effects, momentum, convenience voting, regression discontinuity
Abstract: (click to show/hide) One consequence of the proliferation of vote-by-mail (VBM) in certain areas of the United States is the opportunity for voters to cast ballots weeks before Election Day. Understanding the ensuing effects of VBM on late campaign information loss has important implications for both the study of campaign dynamics and public policy debates on the expansion of convenience voting. Unfortunately, the self-selection of voters into VBM makes it difficult to casually identify the effect of VBM on election outcomes. We overcome this identification problem by exploiting a natural experiment, in which some precincts are assigned to be VBM-only based on an arbitrary threshold of the number of registered voters. We assess the effects of VBM on candidate performance in the 2008 California presidential primary via a regression discontinuity design. We show that VBM both increases the probability of selecting candidates who withdrew from the race in the interval after the distribution of ballots but before Election Day and affects the relative performance of candidates remaining in the race. Thus, we find evidence of late campaign information loss, pointing to the influence of campaign events and momentum in American politics, as well as the unintended consequences of convenience voting.
Meredith, Marc, Malhotra, Neil
Submitted: 2008-10-14
Keywords: Vote by mail, natural experiment, campaign effects, momentum, convenience voting, regression discontinuity
Abstract: (click to show/hide) One consequence of the proliferation of vote-by-mail (VBM) in certain areas of the United States is the opportunity for voters to cast ballots weeks before Election Day. Understanding the ensuing effects of VBM on late campaign information loss has important implications for both the study of campaign dynamics and public policy debates on the expansion of convenience voting. Unfortunately, the self-selection of voters into VBM makes it difficult to casually identify the effect of VBM on election outcomes. We overcome this identification problem by exploiting a natural experiment, in which some precincts are assigned to be VBM-only based on an arbitrary threshold of the number of registered voters. We assess the effects of VBM on candidate performance in the 2008 California presidential primary via a regression discontinuity design. We show that VBM both increases the probability of selecting candidates who withdrew from the race in the interval after the distribution of ballots but before Election Day and affects the relative performance of candidates remaining in the race. Thus, we find evidence of late campaign information loss, pointing to the influence of campaign events and momentum in American politics, as well as the unintended consequences of convenience voting.
What is the probability your vote will make a difference?
Gelman, Andrew, Silver, Nate, Edlin, Aaron
Submitted: 2008-10-27
Keywords:
Abstract: (click to show/hide) One of the motivations for voting is that one vote can make a difference. In a presidential election, the probability that your vote is decisive is equal to the probability that your state is necessary for an electoral college win, times the probability the vote in your state is tied in that event. We compute these probabilities for each state in the 2008 presidential election, using state-by-state election forecasts based on the latest polls. The states where a single vote is most likely to matter are New Mexico, Virginia, New Hampshire, and Colorado, where your vote has an approximate 1 in 10 million chance of determining the national election outcome. On average, a voter in America has a 1 in 60 million chance of being decisive in the presidential election.
Gelman, Andrew, Silver, Nate, Edlin, Aaron
Submitted: 2008-10-27
Keywords:
Abstract: (click to show/hide) One of the motivations for voting is that one vote can make a difference. In a presidential election, the probability that your vote is decisive is equal to the probability that your state is necessary for an electoral college win, times the probability the vote in your state is tied in that event. We compute these probabilities for each state in the 2008 presidential election, using state-by-state election forecasts based on the latest polls. The states where a single vote is most likely to matter are New Mexico, Virginia, New Hampshire, and Colorado, where your vote has an approximate 1 in 10 million chance of determining the national election outcome. On average, a voter in America has a 1 in 60 million chance of being decisive in the presidential election.
What will we know on Tuesday at 7pm?
Gelman, Andrew, Silver, Nate
Submitted: 2008-11-03
Keywords:
Abstract: (click to show/hide) Using 10,000 simulations from a probabilistic election forecast, we compute the conditional distribution of the Obama and McCain's vote margins and electoral vote totals, given the outcomes of the states whose polls are the first to close. We consider the scenario in which the vote margins are available in each state, and separately consider the possibility that we are only told each state's winner.
Gelman, Andrew, Silver, Nate
Submitted: 2008-11-03
Keywords:
Abstract: (click to show/hide) Using 10,000 simulations from a probabilistic election forecast, we compute the conditional distribution of the Obama and McCain's vote margins and electoral vote totals, given the outcomes of the states whose polls are the first to close. We consider the scenario in which the vote margins are available in each state, and separately consider the possibility that we are only told each state's winner.
Foreign Media and Protest Diffusion in Authoritarian Regimes: The Case of the 1989 East German Revolution
Kern, Holger
Submitted: 2008-11-25
Keywords: Germany, media, causal inference, matching, authoritarian, collective action, social movement
Abstract: (click to show/hide) Does access to foreign media facilitate the diffusion of protest in authoritarian regimes? Apparently for the first time, I test this hypothesis by exploiting a natural experiment in communist East Germany. I take advantage of the fact that West German television broadcasts could be received in most but not all parts of East Germany and conduct a matched analysis in which counties without access to West German television are matched to a comparison group of counties with West German television. Comparing these two groups of East German counties, I find no evidence that West German television affected the speed or depth of protest diffusion during the 1989 East German revolution.
Kern, Holger
Submitted: 2008-11-25
Keywords: Germany, media, causal inference, matching, authoritarian, collective action, social movement
Abstract: (click to show/hide) Does access to foreign media facilitate the diffusion of protest in authoritarian regimes? Apparently for the first time, I test this hypothesis by exploiting a natural experiment in communist East Germany. I take advantage of the fact that West German television broadcasts could be received in most but not all parts of East Germany and conduct a matched analysis in which counties without access to West German television are matched to a comparison group of counties with West German television. Comparing these two groups of East German counties, I find no evidence that West German television affected the speed or depth of protest diffusion during the 1989 East German revolution.
