logoPicV1 logoTextV1

Search Results

Below results based on the criteria 'event history'
Total number of records returned: 14

Suspension of the Rules in the House Committee Process
Grant, J. Tobin
Hasecke, Edward B.

Uploaded 05-11-1999
Keywords congressional procedures
legislative organizaiton
event history
Abstract Theories of legislative organization offer competing explanations for the existence and practice of committees in Congress. Not only should these theories explain how bills proceed through committees but also why some bills are considered on the floor without formal committee approval. This paper examines the suspension of the rules procedure, the most common means of considering legislation before formal approval by committees. Using data on every public bill that introduced to the House of Representatives during the 105th Congress, we estimate an event history model of the Speaker's use of suspension of the rules. We test the implications of majority dominant and party dominant theories of legislative organization. We find strong support for the party dominant but not for the majority dominant theory. This finding has implications both our understanding of suspension of the rules and of theories of legislative organization.

Getting the Odds Right: Casino Gaming Diffusion, the Initiative Process and Expected Voter Support
Boehmke, Frederick

Uploaded 10-27-1999
Keywords Initiative
direct democracy
interest groups
event history
casino gaming
formal model
Abstract In this paper I develop and test a formal model of the role that the initiative process plays in shaping policy outcomes. By introducing uncertainty over the median voter's ideal point, I show that the possibility of proposing an initiative makes it cheaper for an interest group to change policy, both through the initiative process and by using contributions to convince the legislature to change policy. By also allowing groups to use information drawn from neighboring states' adoptions to estimate the probability an initiative would pass, I show that policy diffusion should function primarily as information diffusion between initiative states. The predictions of the model are then tested through an event history analysis of state casino gaming legalizations. The initiative process is found to be a positive and significant predictor of adoption and its effect is increased by voter liberalism. There is strong support for the informational approach to diffusion with a positive flow between initiative states and none from or to non-initiative states.

The In-and-Outers Revisited: Duration Analysis and Presidential Appointee Tenure
Tomlinson, Andrew R.
Anderson, William D.

Uploaded 11-09-1999
Keywords presidency
event history
competing risks
Abstract Much has been written about the "fraying" of the Presidential appointments system (NAPA, 1985), but little research has been conducted which takes advantage of recent advancements in event history modeling. The questions posed by many authors in this field focus on two variables -- the time someone spends in office (Joyce, 1990), and the reasons they give for leaving their job (Bonafede, 1987). Not only do event history models avoid the common pitfalls of using OLS to model temporal data (Box-Steffensmeier and Jones, 2000), but certain models allow the researcher to combine temporal data with categorical choice models. We run a simple version of a competing risks model to test the effects of theoretically-chosen covariates on the likelihood of presidential appointees leaving office at a given time. We find support for some hypotheses, specifically those dealing with stress related factors and financial pressures on staffer tenure.

Modelling Space and Time: The Event History Approach
Beck, Nathaniel

Uploaded 08-22-1996
Keywords duration analysis
event history analysis
time-series--cross-section data
discrete duration data
duration dependence
Abstract This is an elementary exposition of duration modelling prepared for a volume in celebration of the 30th anniversary of the Essex Summer School (Research Strategies in the Social Sciences, Elinor Scarbrough and Eric Tanenbaum, editors). The approach is non-mathematical. The running example used is the King et al. model of cabinet durations with particular attention paid to detecting and interpreting duration dependence in that model. There is some new discussion of ascertaining duration dependence using discrete methods and the relationship between discrete duration data and binary time-series--cross-section data.

The Analysis of Binary Time-Series--Cross-Section Data and/or The Democratic Peace
Beck, Nathaniel
Katz, Jonathan

Uploaded 07-18-1997
Keywords binary dependent variable
time-series--cross-section data
serially correlated errors
event history analysis
Abstract The analysis of binary time-series--cross-section (BTSCS) data almost invariably ignores temporal dependence. Using Monte Carlo we show that ordinary probit standard errors underestimate variability in the presence of serially correlated errors. This underestimate, while severe, is smaller than in a corresponding OLS analysis. The simulations show that the standard errors can be partially corrected using Huber's method. We then discuss a variety of other methods for allowing temporal dependency in BTSCS estimation. The simulations show that using a lagged dependent variable will not be the panacea that it is for continuous data. We briefly examine the ``general estimating equation approach.'' We then note the equivalence of BTSCS and event history data, and thus show that common event history techniques which allow for ``duration dependence'' can be used for temporally dependent BTSCS data. The methods are used to re-analyze Oneal and Russett's study of the role of democracy and trade in facilitating peace. After correcting for temporal dependence we still find support for the democratic peace hypothesis but no longer find support for the liberal trade hypothesis.

Covariate Functional Form in Cox Models
Keele, Luke

Uploaded 10-25-2005
Keywords Cox model
event history
survival models
duration models
Abstract In most event history models, the effect of a covariate on the hazard is assumed to have a log-linear functional form. For continuous covariates, this assumption is often violated as the effect is highly nonlinear. Assuming a log-linear functional form when the nonlinear form applies causes specification errors leading to erroneous statistical conclusions. Scholars can, instead of ignoring the presence of nonlinear effects, test for such nonlinearity and incorporate it into the model. I review methods to test for and model nonlinear functional forms for covariates in the Cox model. Testing for such nonlinear effects is important since such nonlinearity can appear as nonproportional hazards, but time varying terms will not correct the misspecification. I investigate the consequences of nonlinear function forms using data on international conflicts from 1950-1985. I demonstrate that the conclusions drawn from this data depend on fitting the correct functional form for the covariates.

Modeling Sample Selection for Durations with Time-Varying Covariates
Boehmke, Frederick

Uploaded 07-02-2008
Keywords selection
selection bias
time-vary covariates
event history
exchange rates
Abstract 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.

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.

First Do No Harm: The Risks of Modeling Temporal Dependence
Dafoe, Allan

Uploaded 07-17-2013
Keywords temporal dependence
repeated events
event history models
lagged dependent variable
Abstract Scholars analyzing repeated-events time-series cross-sectional (TSCS) data for causal inference routinely employ event history models or temporal control variables to address temporal dependence. These methods condition on functions of lags of the outcome, f(LY), to improve causal inference. The appropriate use of such techniques for causal inference rely on assumptions about the data-generating process. The first set of assumptions concerns how one should control for temporal dependence: the functional form, f(LY), must be correctly specified. I examine the study of interstate conflict, showing some ways in which f(LY) is misspecified, and offer suggestions for improving it. The second, deeper, set of assumptions concerns whether one should control for temporal dependence: depending on the cause of temporal dependence, conditioning on f(LY) can worsen estimates. Through the analysis of non-parametric causal graphs and simulations I show that conditioning on f(LY) can reduce bias when temporal dependence arises solely from event dependence, can induce bias when there are unobserved persistent causes of the outcome, and will have ambiguous effects when both causes are present. I present results about the direction of the expected bias, including a bounding result specifying the conditions under which estimates with and without temporal controls will bound the truth. Outside of the experimental ideal, clear causal inference depends on substantive assumptions. Absent strong beliefs about the DGP which justify temporal controls, or a measurable exhaustive un-confounded mechanism generating the temporal dependence, I recommend that scholars routinely report estimates with and without temporal controls; sensitivity to temporal specification implies that a result can not be understood without a better understanding of the temporal dynamics of the phenomenon of interest.

Stochastic Dependence in Competing Risks
Gordon, Sanford C.

Uploaded 09-05-2001
Keywords Competing risks
duration models
survival models
event history
random effects
frailty models
unobserved heterogeneity
Monte Carlo simulation
legislative position-taking
cabinet survival
numeric integration
Markov Chain Monte Carlo
Abstract The term "Competing Risks" describes duration models in which spells may terminate via multiple outcomes: The term of a cabinet, for example, may end with or without an election; wars persist until the loss or victory of the aggressor. Analysts typically assume stochastic independence among risks, the duration modeling equivalent of independence of irrelevant alternatives. However, many political examples violate this assumption. I review competing risks as a latent variables approach. After discussing methods for modeling dependence that place restrictions on the nature of association, I introduce a parametric generalized dependent risks model in which inter-risk correlation may be estimated and its significance tested. The method employs risk-specific random effects drawn from a multivariate normal distribution. Estimation is conducted using numerical methods and/or Bayesian simulation. Monte Carlo simulation reveals desirable large sample properties of the estimator. Finally, I examine two applications using data on cabinet survival and legislative position taking.

The Initiative as a Catalyst for Policy Change
Boehmke, Frederick

Uploaded 03-08-1999
Keywords Initiative
political theory
event history analysis
Abstract In this paper I develop and test a theoretical model of the role that the initiative process plays in shaping policy outcomes. My model builds on Gerber (1996) by introducing uncertainty over the median voter's ideal point and by allowing the interest group to lobby the legislature before a potential initiative is proposed. Successful lobbying may occur due to the uncertainty over the outcome of an initiative. Besides the possibility of lobbying, the results differ from Gerber's since proposal of an initiative is an equilibrium outcome for certain parameter values. I then turn to an event history analysis of state lottery adoptions to test the model's prediction that the initiative process should make it more likely that a state adopt a lottery. This is related to work by Berry and Berry (1990). The empirical hypothesis is found to be supported in the post 1980 period, which I believe is a result of the well-documented resurgence in its use after California's Proposition 13 in 1978. An indirect effect of the initiative in non-initiative states is also found through the importance of neighbors' adoptions. This confirms the view that initiative states are often policy leaders, which I argue may lead to less effective policy choices since they have less information about how to implement then.

Signals, Models, and Congressional Overrides of the Supreme Court
Zorn, Christopher
Hettinger, Virginia

Uploaded 04-05-1999
Keywords event history models
split-population duration models
Supreme Court
statutory decisions
Abstract Sparked by interest in game-theoretic representations of the separation of powers, empirical work examining congressional overrides of Supreme Court statutory decisions has burgeoned in recent years. Much of this work has been hampered, however, by the relative rarity of such events; as has long been noted, congressional attention to the Court is limited, and most Court decisions represent the last word on statutory interpretation. With this fact foremost in our minds, we examine empirically a number of theories regarding such reversals. We apply a split-population duration model to the survival of Supreme Court statutory interpretation decisions. This approach allows us to separate the factors which lead to the event itself (i.e., the presence or absence of an override in a particular case) from those which influence the timing of the event. We find that case-specific factors relating to the salience of a case are an important influence in the incidence of overrides, while Congress- and Court-specific political influences dominate the timing at which those overrides occur. By separating the incidence and timing of overrides, our results yield a more accurate and nuanced understanding of this aspect of the separation of powers system.

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
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.

The Past is Ever-Present: The Dynamic Nature of Intrastate Conflict
Jones, Benjamin

Uploaded 07-28-2012
Keywords Event history
Survival models
Multi-state models
Civil war
Path dependence
Abstract Civil wars pose a grave challenge to international stability as they tend to recur frequently over time. Nevertheless, existing theory treats civil wars as independent events. I reconceptualize civil war as a dynamic process, which creates a new statistical challenge – modeling multi-stage processes through a series of transitions within a longitudinal process. To overcome this problem, I introduce a multi-state event history model, which models the entire civil war process as a series of successive stages in which previous outcomes shape subsequent events, and apply it to a dataset of all civil wars from 1950-2004. The results provide strong evidence that previous outcomes exert both a direct, and indirect effect on subsequent transitions, revealing the conditional nature of factors frequently associated with war and peace.

< prev 1 next>