1

Paper

Causality and Statistical Learning Uploaded 03-16-2010 Keywords causal inference Abstract We review some approaches and philosophies of causal inference coming from sociology, economics, computer science, cognitive science, and statistics

2

Paper

Using Legislative Districting Simulations to Measure Electoral Bias in Legislatures Chen, Jowei Rodden, Jonathan Uploaded 07-19-2010 Keywords redistricting elections legislatures Abstract When one of the major parties in the United States wins a substantially larger share of the seats than its vote share would seem to warrant, the conventional explanation lies in overt partisan or racial gerrymandering. Yet this paper uses a unique data set from Florida to demonstrate a common mechanism through which substantial partisan bias can emerge purely from residential patterns. When partisan preferences are spatially dependent and partisanship is highly correlated with population density, any districting scheme that generates relatively compact, contiguous districts will tend to produce bias against the urban party. We apply automated districting algorithms driven solely by compactness and contiguity parameters, building winner-take-all districts out of the precinct-level results of the tied Florida presidential election of 2000. The simulation results demonstrate that with 50 percent of the votes statewide, the Republicans can expect to win around 59 percent of the seats without any “intentional” gerrymandering. This is because urban districts tend to be homogeneous and Democratic while suburban and rural districts tend to be moderately Republican. Thus in Florida and other states where Democrats are highly concentrated in cities, the seemingly apolitical practice of requiring compact, contiguous districts will produce systematic pro- Republican electoral bias.

3

Paper

Unpacking the Black Box: Learning about Causal Mechanisms from Experimental and Observational Studies Imai, Kosuke Keele, Luke Tingley, Dustin Yamamoto, Teppei Uploaded 07-01-2010 Keywords causal inference direct and indirect effects mediation moderation potential outcomes sensitivity analysis media cues incumbency effects Abstract Understanding causal mechanisms is a fundamental goal of social science research. Demonstrating whether one variable causes a change in another is often insufficient, and researchers seek to explain why such a causal relationship arises. Nevertheless, little is understood about how to identify causal mechanisms in empirical research. Many researchers either informally talk about possible causal mechanisms or attempt to quantify them without explicitly stating the required assumptions. Often, some assert that process tracing in detailed case studies is the only way to evaluate causal mechanisms. Others contend the search for causal mechanisms is so elusive that we should instead focus on causal effects alone. In this paper, we show how to learn about causal mechanisms from experimental and observational studies. Using the potential outcomes framework of causal inference, we formally define causal mechanisms, present general identification and estimation strategies, and provide a method to assess the sensitivity of one's conclusions to the possible violations of key identification assumptions. We also propose several alternative research designs for both experimental and observational studies that may help identify causal mechanisms under less stringent assumptions. The proposed methodology is illustrated using media framing experiments and observational studies of incumbency advantage.

4

Paper

Multiple Overimputation: A Unified Approach to Measurement Error and Missing Data Blackwell, Matthew Honaker, James King, Gary Uploaded 07-19-2010 Keywords measurement error missing data multiple imputation EM overimputation Abstract Social scientists typically devote considerable effort to reducing measurement error during data collection and then ignore the issue during data analysis. Although many statistical methods have been proposed for reducing measurement error-induced biases, few have been widely used because of implausible assumptions, high levels of model dependence, difficult computation, or inapplicability with multiple mismeasured variables. We develop an easy-to-use alternative that generalizes the popular multiple imputation (MI) framework by treating missing data problems as a special case of extreme measurement error and correcting for both. Like MI, the proposed "multiple overimputation" (MO) framework is a simple two-step procedure. First, multiple (around 5) completed copies of the data set are created where cells measured without error are held constant, those missing are imputed from the distribution of predicted values, and cells (or entire variables) with measurement error are ``overimputed,'' that is imputed from a predictive distribution with observation-level priors defined by the mismeasured values and available external information, if any. In the second step, analysts can then run whatever statistical method they would have run on each of the overimputed data sets as if there had been no missingness or measurement error; the results are then combined via a simple procedure. We also offer open source software that implements all the methods described herein.

5

Paper

Election Fraud or Strategic Voting? Can Second-digit Tests Tell the Difference? Mebane, Walter Uploaded 07-06-2010 Keywords election fraud strategic voting gerrymander Benford's Law 2BL American elections turnout presidential House state House state Senate Abstract I simulate a mixture process that generates individual preferences that, when aggregated into precincts, have counts whose second significant digits approximately satisfy Benford's Law. By deriving sincere, strategic, gerrymandered and coerced votes from these preferences under a plurality voting rule, I find that tests based on the second digits of the precinct counts are sensitive to differences in how the counts are derived. The tests can sometimes distinguish coercion from strategic voting and gerrymanders. The tests may be able to distinguish strategic voting according to a party balancing logic from strategic voting due purely to wasted-vote logic, and strategic from nonstrategic voting. These simulation findings are supported by data from federal and state elections in the United States during the 1980s and 2000s.

6

Paper

An Embarrassment of Riches: Parameter Choice in Agent-Based Models Ragan, Robi Uploaded 07-19-2010 Keywords agent-based ABM generative complexity computational emergence Abstract In this paper, I develop a set of criteria that researchers and reviewers may use to determine whether the omission of a parameter in an agent-based computational model calls into question the model’s results. The use of agent-based modeling and other computational modeling techniques is growing within political science. The ability to model without the constraints and associated unrealistic assumptions of traditional analytical techniques has attracted a new generation of scholars. However, now that we are freed from having to make assumptions in order to find closed form solutions or game theoretic equilibria, a new problem arises. Which simplifying assumptions and parameter omissions are still useful, and which should be adjusted? The lack of clear guidelines for this type of question is a hindrance to the acceptance of agent-based models. Every computational modeler makes a fundamental choice with every model: which parameters to include and which to exclude. Most applied methodologists make similar choices: which control variables to include in an estimation in order to isolate the partial effect of an independent variable of interest on the dependent variable. In most cases, there are clear criteria to help an empirical researcher decide. However, when creating a theoretical computational model, the decision is rarely so cut and dry. Often, adding more parameters will do little to change the results generated by the model. In other cases, new parameters radically change the results and may render the model useless. In this paper, I propose a set of criteria for determining which parameters should be included or excluded. I use the analogy of an OLS regression to motivate the discussion. Omitting a parameter that “matters” is likened to omitted variable bias in OLS, and including parameters deemed “unnecessary” is likened to a loss of efficiency due to multi-colinearity. After developing and discussing the set of criteria, I illustrate the point using a set of canonical computational models, including Schelling’s “sorting and mixing” model of housing segregation (Schelling 1978) and Kollman, Miller and Page’s model of Tiebout sorting (1997).

7

Paper

A General Method for Detecting Interference Between Units in Randomized Experiments Aronow, Peter Uploaded 08-17-2010 Keywords Rubin Causal Model SUTVA Permutation test Causal inference Randomization inference Abstract Interference between units may pose a threat to unbiased causal inference in randomized controlled experiments. Although the assumption of no interference is essential for causal inference, few options are available for testing this assumption. This paper presents the first reliable ex post method for detecting interference between units in randomized experiments. Naive estimators of interference that attempt to exploit the proximity of units may be biased because simple randomization of units into treatment does not imply simple randomization of proximity to treated units. However, through a randomization-based approach, the confounding associated with these naive estimators may be circumvented entirely. With a test statistic of the analyst's choice, a conditional randomization test allows for the calculation of the exact significance of the causal dependence of outcomes on the treatment status of other units. The efficacy and robustness of the method is demonstrated through simulation studies and, using this method, interference between units is detected in a field experiment designed to assess the effect of mailings on voter turnout.

8

Paper

Improving Inferences in the Study of Crisis Bargaining Arena, Phil Joyce, Kyle Uploaded 07-19-2010 Keywords crisis bargaining matching instrumental variables structural estimation empirical implications of theoretical models Abstract We present a simple crisis bargaining model that indicates that targets can generally prevent war by arming. We then create a simulated data set where the bargaining model is assumed to perfectly describe the data-generating process for those states engaged in crisis bargaining, which we assume most pairs of states are not. We further assume researchers cannot observe which states are engaged in crisis bargaining, though observable variables might serve as proxies. We demonstrate that a naive design would indicate a positive relationship between arming and war. We then evaluate the ability of matching, instrumental variables, and statistical backwards induction to uncover the true negative relationship. While each method is capable of doing so under certain conditions, each also faces important limitations. In most cases, statistical backwards induction will be the most practical of the three, but we caution that even this method is no perfect fix.

9

Paper

Seven Deadly Sins of Contemporary Quantitative Political Analysis Schrodt, Philip Uploaded 08-23-2010 Keywords collinearity prediction explanation Bayesian frequentist control variables pedagogy philosophy of science logical positivists significance test Hempel Thor Abstract A combination of technological change, methodological drift and a certain degree of intellectual sloth and sloppiness, particularly with respect to philosophy of science,has allowed contemporary quantitative political analysis to accumulate a series of dysfunctional habits that have rendered a great deal of contemporary research more or less scientifically useless. The cure for this is not to reject quantitative methods -- and the cure is most certainly not a postmodernist nihilistic rejection of all systematic method -- but rather to return to some fundamentals, and take on some hard problems rather than expecting to advance knowledge solely through the ever-increasing application of fast-twitch muscle fibers to computer mice. In this paper, these "seven deadly sins" are identified as 1. Kitchen sink models that ignore the effects of collinearity; 2. Pre-scientific explanation in the absence of prediction; 3. Reanalyzing the same data sets until they scream; 4. Using complex methods without understanding the underlying assumptions; 5. Interpreting frequentist statistics as if they were Bayesian; 6. Linear statistical monoculture at the expense of alternative structures; 7. Confusing statistical controls and experimental controls. The answer to these problems is solid, thoughtful, original work driven by an appreciation of both theory and data. Not postmodernism. The paper closes with a review of how we got to this point from the perspective of 17th through 20th century philosophy of science, and provides suggestions for changes in philosophical and pedagogical approaches that might serve to correct some of these problems.

10

Paper

The “Unfriending” Problem: The Consequences of Homophily in Friendship Retention for Causal Estimates of Social Influence Noel, Hans Nyhan, Brendan Uploaded 07-08-2010 Keywords peer effects social networks monte carlo homophily contagion simulation Abstract Christakis, Fowler, and their colleagues have recently published numerous articles estimating “contagion” effects in social networks. In response to concerns that their results are driven by homophily, Christakis and Fowler describe Monte Carlo results showing no evidence of homophily-induced bias in their statistical model’s estimates of peer effects. However, their simulations do not address the role of homophily in friendship retention, which may cause significant problems in longitudinal social network data. We investigate the effects of this mechanism using Monte Carlo simulations and demonstrate that homophily in friendship retention induces significant upward bias and decreased coverage levels in the Christakis and Fowler model if there is non-negligible attrition over time.

11

Paper

Statistical Inference for the Item Count Technique Imai, Kosuke Uploaded 07-19-2010 Keywords list experiments sensitive questions survey experiments unmatched count technique Abstract The item count technique is a survey methodology that is designed to elicit respondents' truthful answers to sensitive questions such as racial prejudice and drug use. The method is also known as the list experiment or the unmatched count technique and is an alternative to the commonly used randomized response method. In this paper, I propose new nonlinear least squares (NLS) and maximum likelihood (ML) estimators for a multivariate analysis with the item count technique. The two-step estimation procedure and the Expectation Maximization algorithm are developed to facilitate the computation. Enabling a multivariate statistical analysis is essential because the item count technique provides respondents with privacy at the expense of statistical efficiency. As an empirical illustration, the proposed methodology is applied to the 1991 National Race and Politics survey where the investigators used the item count technique to measure the degree of racial hatred in the United States. A small-scale simulation study suggests that the ML estimator can be substantially more efficient than the NLS estimator. The software package is made available to implement the proposed methodology.

12

Paper

Geometric construction of voting methods that protect voters' first choices Small, Alex Uploaded 08-23-2010 Keywords Geometry Strategy Gibbard-Satterthwaite Theorem Election Methods Ranked Voting Abstract We consider the possibility of designing an election method that eliminates the incentives for a voter to rank any other candidate equal to or ahead of his or her sincere favorite. We refer to these methods as satisfying the ``Strong Favorite Betrayal Criterion" (SFBC). Methods satisfying our strategic criteria can be classified into four categories, according to their geometrical properties. We prove that two categories of methods are highly restricted and closely related to positional methods (point systems) that give equal points to a voter's first and second choices. The third category is tightly restricted, but if criteria are relaxed slightly a variety of interesting methods can be identified. Finally, we show that methods in the fourth category are largely irrelevant to public elections. Interestingly, most of these methods for satisfying the SFBC do so only ``weakly," in that these methods make no meaningful distinction between the first and second place on the ballot. However, when we relax our conditions and allow (but do not require) equal rankings for first place, a wider range of voting methods are possible, and these methods do indeed make meaningful distinctions between first and second place.

13

Paper

How Much is Minnesota Like Wisconsin? States as Counterfactuals Keele, Luke Minozzi, William Uploaded 07-10-2010 Keywords causal inference voter turnout placebo tests research design Abstract Political scientists are often interested in understanding whether state laws alter individual level behavior. For example, states often alter their election procedures, which can increase or decrease the cost of voting. In this example, it is important to understand whether these changes alter turnout since changes in costs may disproportionally affect those at the margin of voting. Analysts have typically used one of two different regression based research designs to estimate whether changes in state laws increase or decrease turnout. In both instances, voters from states without a change in laws are used as counterfactuals for the voters who experience a change in election law. Here, we carefully examine the assumptions behind both research designs and study their plausibility. Next, we outline a series of research design elements that can be used in addition to the usual designs. These research design elements allow the analyst to better understand the role of unobserved confounders, which is obscured in standard research designs. Using these design elements, we demonstrate that what appears to be clear cut evidence from the usual research designs is often a function confounding. We argue that to truly understand how changes in voting costs alters turnout, a different research design is required. Future work must rely on a research design that makes comparisons among voters who live within the same state. Our work has implications beyond turnout to any investigation of how state level treatments alter individual behavior.

14

Paper

A Statistical Method for Empirical Testing of Competing Theories Imai, Kosuke Tingley, Dustin Uploaded 08-24-2010 Keywords EITM finite mixture model Bayesian statistics multiple testing false discovery rate EM algorithm Abstract Empirical testing of competing theories lies at the heart of social science research. We demonstrate that a very general and well-known class of statistical models, called finite mixture models, provides an effective way of rival theory testing. In the proposed framework, each observation is assumed to be generated from a statistical model implied by one of the theories under consideration. Researchers can then estimate the probability that a specific observation is consistent with either of the competing theories. By directly modeling this probability with the characteristics of observations, one can also determine the conditions under which a particular theory applies. We discuss a principled way to identify a list of observations that are statistically significantly consistent with each theory. Finally, we propose several measures of the overall performance of a particular theory. We illustrate the advantages of our method by applying it to an influential study on trade policy preferences.

15

Paper

No News is News: Non-Ignorable Non-Response in Roll-Call Data Analysis Rosas, Guillermo Shomer, Yael Haptonstahl, Stephen Uploaded 07-10-2010 Keywords rollcall voting abstention missing Bayesian IRT Abstract Roll-call votes are widely employed to infer the ideological proclivities of legislators, even though inferences based on roll-call data are accurate reflections of underlying policy preferences only under stringent assumptions. We explore the consequences of violating one such assumption, namely, the ignorability of the process that generates non-response in roll calls. We offer a reminder of the inferential consequences of ignoring certain processes of non-response, a basic estimation framework to model non-response and vote choice concurrently, and models for two theoretically relevant processes of non-ignorable missingness. We reconsider the "most liberal Senator" question that comes up during election times every four years in light of our arguments and show how we inferences about ideal points can improve by incorporating a priori information about the process that generates abstentions.

16

Paper

Analyzing the robustness of semi-parametric duration models for the study of repeated events models Box-Steffensmeier, Janet Linn, Suzanna Smidt, Corwin Uploaded 08-25-2010 Keywords repeated events event history analysis Abstract Estimators within the Cox family are often used to estimate models for repeated events. Yet there is much we do not know about the performance of these estimators. In particular, we do not know how they perform given time dependence, different censoring rates, varying number of events experienced, and varying sample sizes. We use Monte Carlo simulations to demonstrate the performance of a variety of popular semi-parametric estimators as these things change and also under conditions of event dependence and heterogeneity, both, or neither. We conclude that the conditional frailty model outperforms other standard estimators under a wide array of data-generating processes and conditions.

17

Paper

Misspecification and the Propensity Score: When to Leave Out Relevant Pre-Treatment Variables Clarke, Kevin A. Kenkel, Brenton Rueda, Miguel Uploaded 07-14-2010 Keywords matching propensity scores conditioning omitted variable bias Abstract The popularity of propensity score matching has given rise to a robust, albeit informal, debate concerning the number of pre-treatment variables that should be included in the propensity score. The standard practice is to include all available pre-treatment variables in the propensity score. We demonstrate that this approach is not always optimal for the goal of reducing bias in the estimation of a treatment effect. We characterize conditions under which including an additional relevant variable in a propensity score increases the bias on the effect of interest across a variety of different implementations of the propensity score methodology. We find that matching within propensity score calipers is slightly more robust against such bias than other common methods.

18

Paper

Properties of Ideal-Point Estimators Tahk, Alexander Uploaded 07-20-2010 Keywords ideal points ideal-point estimation consistency Quinn conjecture optimal classification Abstract Although ideal-point estimation has become relatively commonplace in political science, fairly little is known about the properties of these estimations. Two of the most common estimators—NOMINATE and the Bayesian approach of Clinton, Jackman, and Rivers—suffer from the incidental parameters problem, implying that standard results about the consistency of maximum-likelihood and Bayes estimators do not apply. Thus, despite their widespread use, these estimators are not known to be consistent and may lead to erroneous results even in very large samples. This paper provides several theoretical results regarding ideal-point estimation. First, this paper demonstrates a counterexample to consistency of common ideal-point estimators—even with regard to the rank of the ideal points. It then presents a simple estimator of the rank of unidimensional ideal points that is inefficient but also consistent for a generalization of most common ideal-point models.

19

Paper

The Draw Index: A Measure of Competition for Winner-Take-All Elections Rose, Douglas Rose, Douglas Uploaded 08-26-2010 Keywords electoral percentage outcome competition Draw change measure index tie winner-take-all fractionalization winner vote closeness Abstract Winner’s percentage, a common measure of electoral competition in winner-take-all elections, measures the shift in vote shares required to produce changes in election outcome. Thus, winner’s percentage of the vote cast is a logical measure of winner-take-all competition. It treats equally shifts from higher to lower ranking candidates. A related measure, the Draw Index, even more clearly measures vote shifting needed to produce tied, then changed outcomes, with weighting by the preceding ties. A final adjustment, yielding the Draw Plus measure, provides a greater emphasis on the importance of a first change in outcome. Across all cases of five or fewer candidates, five measures of competition – including closeness and Rae’s Index of Fractionalization – are highly correlated. Methods of expanding these measures to include non-voters or no preference are explored in an appendix.

20

Paper

Bargaining Power in Practice: US Treaty-making with American Indians, 1784–1911 Spirling, Arthur Uploaded 07-15-2010 Keywords American Indians Native Americans Text as Data Scaling Kernel methods String Kernels Abstract Native Americans are unique among domestic actors in that their relations with the United States government involve treaty-making, with almost 600 such documents signed between the Revolutionary War and the turn of the twentieth century. We contend that the changing nature of their treaty negotiations can be seen as part of a theoretical, bargaining framework familiar to scholars of international relations. We then construct a comprehensive new data set by digitizing all of the treaties for systematic textual analysis. Employing scaling techniques validated with word use information, we show that a single dimension characterizes the treaties as more or less 'harsh' in land and resource cession terms. With a mind to earlier historical and legal literatures, we also show that the 'broken' treaties are not obviously distinguishable from contemporaneous valid ones, and that the post-1871 'agreements' represent a straightforward continuation of earlier treaty policy in both style and substance. In bargaining terms, we find evidence suggestive of a detrimental 'losing' effect for Indians involved in war with the US.

21

Paper

Automated Production of High-Volume, Near-Real-Time Political Event Data Schrodt, Philip Uploaded 08-30-2010 Keywords event data ICEWS DARPA natural language processing open source forecasting prediction conflict Abstract This paper summarizes the current state-of-the-art for generating high-volume, near-real-time event data using automated coding methods, based on recent efforts for the DARPA Integrated Crisis Early Warning System (ICEWS) and NSF-funded research. The ICEWS work expanded by more than two orders of magnitude previous automated coding efforts, coding of about 26-million sentences generated from 8-million stories condensed from around 30 gigabytes of text. The actual coding took six minutes. The paper is largely a general ``how-to'' guide to the pragmatic challenges and solutions to various elements of the process of generating event data using automated techniques. It also discusses a number of ways that this could be augmented with existing open-source natural language processing software to generate a third-generation event data coding system.

22

Paper

New Empirical Strategies to Model the Government Formation Process Glasgow, Garrett Golder, Matt Golder, Sona Uploaded 07-15-2010 Keywords discrete choice mixed logit IIA random coefficients government formation Abstract Over the past decade, a "standard approach" to the quantitative study of government formation has developed. This approach involves the use of a conditional (CL) logit model to examine government choice with the government formation opportunity as the unit of analysis. In this paper, we reconsider this approach and make three methodological contributions. First, we demonstrate that the existing procedure used to test for the independence of irrelevant alternatives (IIA) is flawed and severely biased against finding IIA violations. Our new testing procedure reveals that many government alternatives share unobserved attributes, thereby violating the IIA assumption and making the CL model inappropriate. Second, we employ a mixed logit with random coefficients that allows us to take account of unobserved heterogeneity and IIA violations. Third, we return to a question that originally motivated this literature, namely, what determines the likelihood that a particular party enters government? Although scholars have generally abandoned this question due to perceived methodological limitations in our ability to address it, we demonstrate that calculating probabilities for parties entering office rather than governments is straightforward in a mixed logit framework.

23

Paper

Bayesian Methods: A Social and Behavioral Sciences Approach, ANSWER KEY TO THE SECOND EDITION. Odd Numbers. Park, Hong Min Gill, Jeff Uploaded 09-14-2010 Keywords Bayes modeling simulation Bayesian inference MCMC prior posterior Bayes Factor DIC GLM Markov chain Monte Carlo hierarchical models linear nonlinear Abstract This is the odd-numbered exercise answers to the second edition of Bayesian Methods: A Social and Behavioral Sciences Approach (minus Chapter 13). Course Instructors can get the full set from Chapman & Hall/CRC upon request.

24

Paper

Formal Tests of Substantive Significance for Linear and Non-Linear Models Esarey, Justin Danneman, Nathan Uploaded 07-16-2010 Keywords statistical decision theory substantive significance marginal effects bayesian Abstract We propose a critical statistic c^{*} for determining the substantive significance of an empirical result, which we define as the degree to which it justifies a particular decision (such as the decision to accept or reject a theoretical hypothesis), and provide software tools for calculating c^{*} for a wide variety of models. Our procedure, which is built on ideas from Bayesian statistical decision theory, helps researchers improve the objectivity, transparency, and consistency of their assessments of substantive significance.

25

Paper

An Empirical Justification for the Use of Draft Lottery Numbers as a Random Treatment in Political Science Research Berinsky, Adam Uploaded 10-18-2010 Abstract In a series of papers in the 1990s, Joshua Angrist and Alan Krueger (1991, 1992) sparked interest in the use of the draft lotteries held with the United States in the late 1960s and early 1970s as an instrument for economic outcomes. Over the last few years, there has been growing use of the draft lottery instrument within political science to study political attitudes and behaviors. The lottery is indeed a potentially powerful design because, if conducted correctly, it should provide true randomization for the “treatment” of military service (or behavioral reactions to the threat of such service). However, the first draft lottery conducted in 1969 was not conducted in a truly random manner. Because the Selective Service officials employed faulty procedures, the randomization failed. As a result, those men with birthdates at the end of the year were more likely to have low draft numbers than citizens with birthdates earlier in the year (meaning that they were more likely to be called to service). Previous research suggests that people born at the end of the year are different on key demographic markers than those born earlier in the year. Given the nature of the randomization failure in 1969, the use of draft lottery numbers could confound the effect of the draft with established quarter-of-birth effects. In practice, though, there are small and largely statistically insignificant differences on politically relevant variables between those individuals born early in the year and those born later in the year. Thus, researchers can treat the 1969 draft lottery numbers as if they were assigned at random. However, to account for unmeasured differences based on quarter of birth, I suggest that when using draft numbers as instruments in analyses, researchers should include robustness tests which include measures for the respondents’ quarter or month of birth.

26

Paper

Invaluable Involvement: Purposive Interest Group Networks in the 21st Century Uploaded 02-04-2010 Keywords Network Analysis Interest Groups Amicus Curiae Coalition Strategy Abstract We present the first comprehensive social network analysis of purposive and coordinated interest group relationships. We utilize a network measure based on cosigner status to United States Supreme Court amicus curiae, or friend of the court briefs. The illuminated structures lend insight into the central players and overall formation of the network over the first seven years of the 21st century. We find that the majority of interest groups primarily partake in coalition strategies with other groups of similar policy interest and ideological character. This is in contrast to previous literature that focused only on one or the other. Network analysis provides evidence, for example, that the National Wildlife Foundation, the National Association of Criminal Defense Lawyers and the American Civil Liberties Union are all particularly strong groups, but exploit different central roles.

27

Paper

Detecting heterogeneous treatment effects in large-scale experiments using Bayesian Additive Regression Trees Green, Donald Kern, Holger Uploaded 07-16-2010 Keywords causal inference heterogeneity ATE ensemble methods BART tree models MCMC Abstract We present a method that largely automates the search for systematic treatment effect heterogeneity in large-scale experiments. We introduce an estimator recently proposed in the statistical learning literature, Bayesian Additive Regression Trees (BART), to model treatment effects that vary as a function of covariates. BART has two important advantages over commonly employed parametric modeling strategies: it automates the search for treatment-covariate interactions and models them in a very flexible manner. To increase the reliability and credibility of the resulting conditional average treatment effect estimates, we suggest the use of a split sample analysis, which randomly divides the data into two equally-sized parts. The first part is used to search for systematic treatment effect heterogeneity; the second part is used to confirm the results. This approach permits a relatively unstructured exploration of systematic treatment effect heterogeneity while avoiding the pitfalls of data dredging and multiple comparisons. We illustrate the value of our approach by offering two empirical examples, a survey experiment on Americans' support for social welfare spending and a voter mobilization field experiment. In both applications, our approach provides robust insights into the nature and extent of systematic treatment effect heterogeneity.

28

Paper

Modeling History Dependence in Network-Behavior Coevolution Franzese, Robert Hays, Jude Kachi, Aya Uploaded 07-21-2010 Keywords path dependence history dependence network coevolution spatial econometrics selection homophily SIENA RSIENA markov chain logit p-star military alliance conflict behavior Abstract Spatial interdependence--the dependence of outcomes in some units on those in others--is substantively and theoretically ubiquitous and central across the social sciences. Spatial association is also omnipresent empirically. However, spatial association may arise from three importantly distinct processes: common exposure of actors to exogenous external and internal stimuli, interdependence of outcomes/behaviors across actors (contagion), and/or the putative outcomes may affect the variable along which the clustering occurs (selection). Accurate inference about any of these processes generally requires an empirical strategy that addresses all three well. From a spatial-econometric perspective, this suggests spatiotemporal empirical models with exogenous covariates (common exposure) and spatial lags (contagion), with the spatial weights being endogenous (selection). From a longitudinal network-analytic perspective, we can identify the same three processes as potential sources of network effects and network formation. From that perspective, actors' self-selection into networks (by, e.g., behavioral homophily) and actors' behavior that is contagious through those network connections likewise demands theoretical and empirical models in which networks and behavior coevolve over time. This paper begins building such modeling by, on the theoretical side, extending a Markov type-interaction model to allow endogenous tie-formation, and, on the empirical side, merging a simple spatial-lag logit model of contagious behavior with a simple p-star logit model of network formation, building this synthetic discrete-time empirical model from the theoretical base of the modified Markov type-interaction model. One interesting consequence of network-behavior coevolution--identically: endogenous patterns of spatial interdependence--emphasized here is how it can produce history-dependent political dynamics, including equilibrium phat and path dependence (Page 2006). The paper explores these implications, and then concludes with a preliminary demonstration of the strategy applied to alliance formation and conflict behavior among the great powers in the first half of the twentieth century.

29

Paper

The Immigration Issue and the 2010 House Elections: A Research Design Monogan, Jamie Uploaded 11-02-2010 Keywords causal inference propensity score elections immigration Abstract This paper proposes a research design for evaluating the effect of Republican candidates' immigration stances on House election outcomes. It develops a measure of immigration stance which is based on the text of each candidate's issue statement. With this as the treatment, propensities to support a harsh line on immigration are calculated for each candidate based on a variety of covariates that also may influence election outcomes. In this way, a research design is developed before election outcomes are observed. Thus, this project clearly reflects the advice of Rubin, who argues that the research design ought to be set before the outcome is even observed.

30

Paper

Penalized Regression, Standard Errors, and Bayesian Lassos Kyung, Minjung Gill, Jeff Ghosh, Malay Casella, George Uploaded 02-23-2010 Keywords model selection lassos Bayesian hierarchical models LARS algorithm EM/Gibbs sampler Geometric Ergodicity Gibbs Sampling Abstract Penalized regression methods for simultaneous variable selection and coefficient estimation, especially those based on the lasso of Tibshirani (1996), have received a great deal of attention in recent years, mostly through frequentist models. Properties such as consistency have been studied, and are achieved by different lasso variations. Here we look at a fully Bayesian formulation of the problem, which is flexible enough to encompass most versions of the lasso that have been previously considered. The advantages of the hierarchical Bayesian formulations are many. In addition to the usual ease-of-interpretation of hierarchical models, the Bayesian formulation produces valid standard errors (which can be problematic for the frequentist lasso), and is based on a geometrically ergodic Markov chain. We compare the performance of the Bayesian lassos to their frequentist counterparts using simulations and data sets that previous lasso papers have used, and see that in terms of prediction mean squared error, the Bayesian lasso performance is similar to and, in some cases, better than, the frequentist lasso.

31

Paper

Inferring Strategic Voting Kawai, Kei Watanabe, Yasutora Uploaded 07-16-2010 Keywords Strategic Voting Set Estimation Partial Identification Abstract We estimate a model of strategic voting and quantify the impact it has on election outcomes. Because the model exhibits multiplicity of outcomes, we adopt a set estimator. Using Japanese general-election data, we find a large fraction [75.3%, 80.3%] of strategic voters, only a small fraction [2.4%, 5.5%] of whom voted for a candidate other than the one they most preferred (misaligned voting). Existing empirical literature has not distinguished between the two, estimating misaligned voting instead of strategic voting. Accordingly, while our estimate of strategic voting is high, our estimate of misaligned voting is comparable to previous studies.

32

Paper

When is it rational to redistribute? A cross-national examination of attitudes toward redistribution Dion, Michelle Uploaded 07-22-2010 Keywords income inequality redistribution public opinion Abstract Much political economy work on the politics of public policy and particularly redistribution builds on an assumption that individual income is negatively related to demand for redistribution. Since aggregate income inequality is not positively related to aggregate redistribution cross-nationally, various efforts seek to understand why political institutions fail to efficiently aggregate citizen preferences. This paper approaches this puzzle from a different perspective, instead seeking to understand the ways economic, social, and political context may shape preference formation and condition the individual-level relationship between income and demand for government redistribution. Using 300 country-surveys in 50 countries between 1985 and 2008 to model the relationships among country-level characteristics, individual income and support for redistribution, this paper finds evidence to suggest that not only do political institutions, inequality, and existing redistribution shape the formation of preferences, but that social diversity and dominant cultural values do as well.

33

Paper

The Democracy Paradox Gagnon, Jean-Paul Gagnon, Jean-Paul Uploaded 02-24-2010 Keywords democracy theory political science governance problems paradox what is democracy Abstract This paper argues that democracy is a governing method endemic to human nature. It also argues that since democracy�??s growth and stylizations (for example by the Mycenaeans, Greek, Ottoman, and later the modern post-colonial world) it has been misunderstood and incorrectly defined. At present, many scholars (such as Beetham, Breton, Dahl, Diamond, Huntington, Keane, and to a certain extent Touraine) seek to explain democracy as theorists and philosophers have been trying to do for millennia. The lack of explaining the general laws of democracy in a universally accepted definition is a major crux in political theory. The current political science focus on indices which appoint performance scores regarding how �??democratic�?? a country is reveals another example of how, increasingly, more mainstream political thinking seeks to define democracy with general criteria (evincing a desire to appoint universal laws to democracy). This paper will show that there is, and has been for well over 3500 years, a democracy paradox by explaining what it is and how it came about. Such will be done firstly by revealing the history of the paradox; then discussing how it came to the modern era without being solved; finishing with the answer to the paradox derived from the author�??s doctoral thesis.

34

Paper

Polity by Design; an engineering approach Kwatra, Saurabh Uploaded 03-15-2010 Keywords Genuine Political Engineering Good Governance Interdisciplinary Designing Abstract Rules by which societies govern themselves are called institutions. Institutions can be political, economic, social, but generally they are a complex combination of these. Universities and academies of higher education frequently offer courseware on 'Political Engineering'; the title has an interdisciplinary flavor, suggesting some kind of engineering applied to political science. When you proceed from heading to subject, you find tools of economic theory, game theory, social-choice theory and formal logic used in ample. There is everything but engineering! This paper is the first bold attempt to apply genuine methodologies in mechanical engineering design to Governance. Hence I define this created subject as �??Genuine Political Engineering�??. The paper revolves around the solution to a complex problem: comparing the size of a road roller required resurfacing a road most efficiently with the number of elected representatives required ruling a population (in a country or state) most effectively. The solution emerges in the shape of a sophisticated software that I call 'political machinery'. This research is aimed to compel a sizeable percentage of conventional political pundits and exponents of sustainable living to conclude that governance can be bettered by employing machine designers to assist parliamentarians-turned-policy makers.

35

Paper

What Can We Learn with Statistical Truth Serum? Design and Analysis of the List Experiment Glynn, Adam Uploaded 07-23-2010 Keywords social desirability indirect questions list experiment item count technique privacy protection survey experiment Abstract Due to the inherent sensitivity of many survey questions, a number of researchers have adopted an indirect questioning technique known as the list experiment (or the item count technique) in order to minimize bias due to dishonest or evasive responses. However, standard practice with the list experiment requires a large sample size, is not readily adaptable to regression or multivariate modeling, and provides only limited diagnostics. This paper addresses all three of these issues. First, the paper presents design principles for the standard list experiment (and the double list experiment) to minimize bias and reduce variance as well as providing sample size formulas for the planning of studies. Additionally, this paper investigates the properties of a number of estimators and introduces an easy-to-use piecewise estimator that reduces necessary sample sizes in many cases. Second, this paper proves that standard-procedure list experiment data can be used to estimate the probability that an individual holds the socially undesirable opinion/behavior. This allows multivariate modeling. Third, this paper demonstrates that some violations of the behavioral assumptions implicit in the technique can be diagnosed with the list experiment data. The techniques in this paper are illustrated with examples from American politics.

36

Paper

"How many zombies do you know?" Using indirect survey methods to measure alien attacks and outbreaks of the undead Gelman, Andrew Uploaded 03-16-2010 Abstract The zombie menace has so far been studied only qualitatively or through the use of mathematical models without empirical content. We propose to use a new tool in survey research to allow zombies to be studied indirectly without risk to the interviewers.

37

Paper

Measuring Political Support and Issue Ownership Using Endorsement Experiments, with Application to the Militant Groups in Pakistan Bullock, Will Imai, Kosuke Shapiro, Jacob Uploaded 07-18-2010 Keywords endorsement experiment survey experiment bayesian pakistan militant groups issue ownership social desirability Abstract To measure the levels of support for political actors (e.g., candidates and parties) and the strength of their issue ownership, survey experiments are often conducted in which respondents are asked to express their opinion about a particular policy endorsed by a randomly selected political actor. These responses are contrasted with those from a control group that receives no endorsement. This survey methodology is particularly useful for studying sensitive political attitudes. We develop a Bayesian hierarchical measurement model for such endorsement experiments, demonstrate its statistical properties through simulations, and use it to measure support for Islamist militant groups in Pakistan. Our model uses item response theory to estimate support levels on the same scale as the ideal points of respondents. The model also estimates the strength of political actors' issue ownership for specic policies as well as the relationship between respondents' characteristics and support levels. Our analysis of a recent survey experiment in Pakistan reveals three key patterns. First, citizens' attitudes towards militant groups are geographically clustered. Second, once these regional differences are taken into account, respondents' characteristics have little predictive power for their support levels. Finally, militant groups tend to receive less support in the areas where they operate.

38

Poster

Do you feel Angry? Are you sure? Testing the Reliability of Overt Emotional Cues and the Effects of Semantic Self Reports in Experimental Research Searles, Kathleen Uploaded 07-24-2010 Keywords experiment affect semantic prompt Abstract In the experimental study of political affect two assumptions are implicit. First, scholars assume that the affective state intended by the treatment is actually invoked. Second, scholars assume that semantic prompts such as, “Has (Barack Obama/John McCain) -- because of the kind of person he is, or because of something he has done -- ever made you feel: (insert word from feeling scale),” provide an accurate reliability check on the former assumption. However, work in psychology demonstrates that the use of semantic self reports is unreliable because participants do poorly at accurately reporting experienced emotion (Breckler 1984; Shacter and Singer 1962; Weber et al. 2007). If the presence of the prompt introduces error into the model or participants do not reliably recall their affective state then the use of semantic affective prompts is problematic. I ask: Q1: Is the semantic affective prompt an effective check on the reliability of an emotional cue? Additionally, I examine the use of overt anger cues versus subliminal anger cues in eliciting anger. Though most scholars use semantic self-reports as a direct test that the emotion of interest was elicited, others use subliminal primes to elicit emotional states outside of awareness (Bargh 1997). I ask: Q2: Is there a significant difference between models that invoke emotion overtly versus subliminally? I utilize a unique research design to tease out the effects of interest. To do so I set up treatment conditions which vary in the way the affective state is invoked (overtly/subliminally) and in the presence or absence of a semantic affective prompt. If find that challenges to the use of the semantic affective prompt are warranted: there is a mean difference in the responses of participants assigned to the semantic affective prompt condition and participants assigned to the no affective prompt condition.

39

Poster

Economic Voting: Causal Mediation of Retrospective Evaluations Becher, Michael Donnelly, Michael Uploaded 08-15-2010 Keywords Economic Voting Causal Mediation Mediation Incumbency Retrospective Evaluations Ideology Abstract In this paper, we show that an increase in economic growth has a positive effect on the share of voters who support the party of the chief executive and that it does this through retrospective evaluations of the economy. In order to do this, we expand on the results of Duch and Stevenson (2005, 2008). Using causal mediation analysis, we show that an increase in economic growth leads to an increase in the number of survey respondents whose retrospective evaluations of the economy are positive. This, in turn, leads to an increase in the number of voters who support the party of the chief executive. A similar result holds using annual unemployment change as the treatment. In both cases, the effect is weaker when the chief executive is a member of a coalition. The evidence for existence of mediation effects is robust to the inclusion or exclusion of a number of control variables, including an interaction between individual ideology and government ideology.

40

Poster

A Comparison of Instrumental Variable Estimators in Models of Discrete Choice Quiroz Flores, Alejandro Uploaded 07-08-2010 Keywords instrumental variables discrete choice probit model continuous endogenous regressors MLE Newey Two-step GMM Abstract Comparison of three instrumental variable estimators applicable to probit models. The first estimator uses conditional probabilities and MLE. The second estimator uses Newey’s two-step minimum chi-squared estimator. A new estimator presented here uses GMM to approach probit models as non-linear regression. These models are compared in a simulation experiment. Results show that conditional probability MLE model has superior performance both in terms of bias and efficiency, although the GMM estimator follows closely.

41

Poster

A Bottom-Up Approach to Linguistic Persuasion in Advertising Beauchamp, Nick Uploaded 07-20-2010 Keywords persuasion opinion election voting text campaign scaling advertising Abstract This paper presents a new, bottom-up approach to understanding how the linguistic contents of television advertisements determine their persuasive effects. Rather than categorizing by topic or style the hundreds of ads run during a presidential election campaign, and then working with a few ad categories as independent variables, this approach instead estimates an effect for each unique ad and then draws inferences about the relationship between the contents of those ads and their effects using automated text analysis. Specifically, each unique ad run in 2004 is assigned its own variable (counting broadcasts per region per time), and since regressing (survey-measured) vote intention on all the ad variables at once would result in severe over-fitting, instead each ad variable is regressed separately, and vote intention is predicted by averaging the individual predictions. This approach is validated through extensive out-of-sample testing of predicted versus measured vote intention, and the collective effect of all ads is shown to be significant and largely pro-Democrat in 2004. To understand what in the content of those ads determines their varying effects, a variety of automated text analyses (eg, k-nearest-neighbor, distance weighting, and Bayesian) are adapted to predict ad effects based on the textual similarity between new ads and previously measured ads, and the technique is again validated through out-of-sample testing. The most effective pro-Democrat and pro-Republican words are established using a one-dimensional scaling of words in the ad-effect space, with suggestive differences between the two word sets. This new approach is of substantive interest for the insights the text analysis provides about why ads differ in their effects, and it is of methodological interest in grounding automated text analysis in a framework that allows real-world prediction and out-of-sample testing. The tools developed could also be of practical use in shaping future advertising campaigns.

42

Poster

Optimally Selecting Matched Samples Nielsen, Rich Uploaded 07-20-2010 Keywords Matching CEM Propensity Score Calipers Abstract We apply a new and simple graphical method (the ``space graph"; Iacus, King, and Porro, 2010) for evaluating many matched samples and selecting the best one(s). We then use this technique to reveal patterns in the relative performance of matching methods across data sets. We also identify an important and previously unnoticed problem that causes propensity score matching with calipers to fail in precisely the applications for which it was designed.

43

Poster

Weighted Estimation for Analyses with Missing Data Samii, Cyrus Uploaded 07-21-2010 Keywords missing data doubly robust inverse probability weighting semi-parametric post-treatment regression sample selection Abstract Missing data plague data analyses in political science. The recent applied statistics literature reflects renewed interest in weighting methods for missing data problems. Three properties are stressed in this literature: (i) robustness, (ii) the ability to use post-treatment information in causal analysis, and (iii) methods to gain efficiency. I present these results, hoping to show the potential in using refashioned weighting methods for political science research.

44

Poster

Parties, Pivots, and Policy: The Status Quo Test Richman, Jesse Uploaded 07-21-2010 Abstract This study applies a novel technique that measures policy status quo locations in relation to legislators’ preferences. The resulting status quo estimates allow for the first direct test of the policy consequences predicted by the pivotal politics and party cartel theories of legislative politics. The empirical tests indicate that parties interact with pivotal politics to contribute to policy gridlock and shape policy change. By bringing pressure to bear upon pivotal politics pivots and by blocking policy changes that would ‘roll’ the party, parties increase the range of policies subject to gridlock in the American political system.

45

Poster

Inferring Strategic Voting Watanabe, Yasutora Kawai, Kei Uploaded 07-21-2010 Keywords Strategic Voting Partial Identificatioin Set Estimation Abstract We estimate a model of strategic voting and quantify the impact it has on election outcomes. Because the model exhibits multiplicity of outcomes, we adopt a set estimator. Using Japanese general-election data, we find a large fraction [75.3%, 80.3%] of strategic voters, only a small fraction [2.4%, 5.5%] of whom voted for a candidate other than the one they most preferred (misaligned voting). Existing empirical literature has not distinguished between the two, estimating misaligned voting instead of strategic voting. Accordingly, while our estimate of strategic voting is high, our estimate of misaligned voting is comparable to previous studies.

46

Poster

Effects of Interviewer Gender and Hijab on Gender-Related Survey Responses: Findings from a Nationally-Representative Field Experiment in Morocco Benstead, Lindsay Uploaded 11-07-2010 Keywords Gender of Interviewer Effects Response Effects Interviewer Religious Dress Hijab Morocco Middle East Missing Data North Africa Women's Rights Muslim World Abstract Despite the recent expansion of surveying in the Muslim world, few published studies have addressed methodological questions, including how observable interviewer characteristics affect responses and data quality. Although there are a limited number of studies on interviewer dress effects, none examine interviewer gender. This study asks whether and why gender and religious dress affect responses to gender-related questions. Drawing upon original data from a nationally-representative, partially-randomized survey of 800 Moroccans conducted in 2007, the study finds strong evidence that gender and dress affect responses and item non-response. The paper argues that because hijab implies multiple personal, religious, and political dimensions of identity nested within gender identity, interviewer gender and dress must be considered as intersecting categories. For questions pertaining to women’s role in the public sphere, responses were affected by interviewer dress; respondents reported more progressive attitudes and were more likely to refuse to respond to female interviewers not wearing hijab than to veiled female interviewers and male interviewers. For support for gender equality in family law, results were affected by interviewer gender; respondents reported more liberal views and were more likely to fail to respond to female interviewers with both dress styles than male interviewers. Interviewer characteristics affected responses to more than half of the 174 questions included in the survey, including support for democracy and religiosity. Researchers conducting surveys should code and control for interviewer characteristics in order to reduce total survey error and better understand the social processes which generate public opinion in this crucial region.

47

Poster

Robust Estimation of the Cox Proportional Hazards Model Harden, Jeff Uploaded 07-17-2010 Keywords Event History Modeling Cox Proportional Hazards Model Partial Likelihood Maximization Iteratively-Reweighted Robust Estimation Cross-Validation Abstract The Cox proportional hazards model is often used with time-to-event data in political science. However, misspecification issues such as measurement error or omitted covariates can cause substantial coefficient bias when it is estimated via the conventional Partial Likelihood Maximization (PLM). Here we review an iteratively-reweighted robust (IRR) estimator of the Cox model that is proven to reduce this bias under such conditions and propose a cross-validated median fit (CVMF) test to select between PLM and IRR. Then we apply the test to data in political science. We consider several typologies of replications with respect to (1) the test's selection (PLM or IRR) and (2) the implications of IRR for the original hypotheses (less support, more support, or mixed results). Overall, we demonstrate that PLM and IRR can each be optimal, that substantive conclusions can depend on which one is used, and that the CVMF test is effective in choosing between them.

48

Poster

A New Solution to Ecological Inference Huang, Min-Hua Uploaded 07-22-2010 Keywords Ecological Inferefce Gaussian Integral Exponential Integral Gamma Function Truncated Normal Distribution Error Distribution Abstract This poster presents a new solution to ecological inference (the example of southern vote registration, King, 1997). It solves the ecological regression directly with the maximum likelihood method and a mathematical solution to the bounded Gaussian integral. Assuming the proportion of black voters Xi and the overall voter's turnout Ti normally distributed between (0,1), the error distribution can be mathematically deduced from tomography lines as normally distributed with a doubly truncation , where Bb and Bw (the percentage of black's and white's turnout) is fixed. Given the analytical form of the error distribution has been known, we can directly solve the regression through MLE and derive an analytical solution to the Ecological Inference problem.

49

Poster

Non-Parametric Treatment Effect Estimation Strategy for Missing Treatment Data Poast, Paul Uploaded 07-17-2010 Keywords Classic Treatment Effect Manski Bounds Non-parametrics Abstract What should scholars do when faced with missing treatment data in randomized experiments or observational studies? Rather than, for example, assuming the treatment data is missing at random, Molinari (2010) introduces a non-parametric approach for computing bounds on treatment effects when there are missing treatment data. I review the Molinari approach and then use it to address an important question in international relations: is it true that ``issue linkage'' (the simultaneous negotiation of multiple issues for joint settlement) helps states conclude otherwise unattainable negotiated agreements?

50

Poster

Beyond Voting: A Generalized Model of Political Participation Levin, Ines Uploaded 07-23-2010 Keywords political participation latent class analysis finite mixture modeling random utility models scobit Abstract For decades political scientists have studied the motives underlying individual engagement in political activities, but the field still lacks a comprehensive study taking into account the commonalities between different forms of political engagement. It is likely that some of the factors that affect the decision to vote also affect the choice of working for a campaign or donating money, as well as engagement in other political endeavors. In this paper I construct a model that allows measuring how observed individual attributes influence decisions to participate specific activities, as well as identifying common patterns of behavior across different form of activism. Most importantly, since empirical models cannot possibly account for all factors affecting participation decisions, and since other factors are likely to follow heterogeneous distributions across the population, I develop a generalized specification where respondents are classified into classes with lower or greater propensities toward civic voluntarism depending on the distribution of unobserved attributes. If underlying heterogeneities have considerable effects on propensities toward participation, learning about these heterogeneities is important for gaining a better understanding of how well activists and elected candidates represent diverse constituencies, and is also useful for the design of mobilization campaigns. I applied this model to survey data collected during the 2008 electoral period and found that while a relatively small proportion of individuals exhibited high propensity toward participation and were fairly sensitive to variations in variables such as education attainment, most respondents were assigned to a group with low tendencies toward activism and low sensitivity to changes in observable attributes.