We study the properties of a three-step approach to estimating the parameters of a latent structure model for categorical data and propose a simple correction for a common source of bias. Such models have a measurement part (essentially the latent class model) and a structural (causal) part (essentially a system of logit equations). In the three-step approach, a stand-alone measurement model is first defined and its parameters are estimated. Individual predicted scores on the latent variables are then computed from the parameter estimates of the measurement model and the individual observed scoring patterns on the indicators. Finally, these predicted scores are used in the causal part and treated as observed variables. We show that such a naive use of predicted latent scores cannot be recommended since it leads to a systematic underestimation of the strength of the association among the variables in the structural part of the models. However, a simple correction procedure can eliminate this systematic bias. This approach is illustrated on simulated and real data. A method that uses multiple imputation to account for the fact that the predicted latent variables are random variables can produce standard errors for the parameters in the structural part of the model.

Borrowing an approach from the literature on the economics of discrimination, we estimate the impact of nonvoters on the outcome of presidential elections from 1952–2000 using data from the National Election Study (NES). Our estimates indicate that nonvoters are, on average, slightly more likely to support the Democratic Party. Of the 13 presidential elections between 1952 and 2000 we find no change in the eventual outcome of the election with two possible exceptions: 1980 and 2000. Thus our results are not all that dissimilar from other research on participation. Higher turnout in the form of compulsory voting would not radically change the partisan distribution of the vote. When elections are sufficiently close, however, a two percentage point increase may suffice to affect the outcome. Limitations of the NES data we use suggest that our estimates underestimate the impact of nonparticipation. We also compare our method with other econometric techniques. Finally, using our findings we speculate as to why the Democratic Party fails to undertake widespread “get out the vote” or registration drives.

An important property of any party system is the set of choices it presents to the electorate. In this paper we analyze the distribution of parties relative to voters in the multidimensional issue space and introduce two measures of the dispersion of the parties in the issue space relative to the voters, which we call measures of the compactness of the parties in the issue space. We show how compactness is easily computed using standard survey items found on national election surveys. Because we study the spacing of the parties relative to the distribution of the voters, we produce metric-free measures of compactness of the party system. The measures can be used to compare party systems across issues, over time within countries, and across countries. Comparing the compactness of party systems across countries allows us to determine the relative amount of issue choice afforded voters in different polities. We examine the compactness of the issue space and test the impact it has on voter choice in four countries: the United States, the Netherlands, Canada, and Great Britain. We demonstrate that the more compact the distribution of the parties in the issue space on any given issue, the less voters weight that issue in their vote decision. Thus we provide evidence supporting theories suggesting that the greater the choice offered by the parties in an election, the more likely it is that issue voting will play a major role in that election.

This paper presents a method for using dimensional reduction in the analysis of political content. We draw inspiration from latent semantic analysis (LSA) theory, which posits that factor analysis can successfully model human language. We suggest that the factor analysis of word frequencies generated from any political text—for example, open-ended survey responses—provides adequate content analysis categories and can substitute for more commonly practiced techniques. The method proceeds in three steps: data preparation, exploratory factor analyses, and hypothesis testing. This method may produce other benefits by allowing the data to speak more clearly in the development of coding dictionaries while avoiding the problems of inferential circularity common in other data-driven approaches. We demonstrate the method using responses collected in the execution of an experimental design dealing with the topic of partial-birth abortion and assess the demonstration by presenting a human coding of the same material.

This article investigates the effect of social conformity on voting behavior. Past research shows that many people vote to conform with the social norm that voting is a civic duty. The hypothesis here is that when conformity motivates people to vote, it also stimulates conformist behavior among some voters when they decide which party to vote for. This produces a distinctive relationship between voter turnout and the distribution of votes among parties—a relationship not anticipated by rational choice theory. I test a mathematical model of this behavior with linear and nonlinear regression analyses of state-level data for presidential elections in the United States from 1904 to 1996, longitudinal data on parliamentary elections in Western Europe over most of the twentieth century, and cross-sectional data for recent elections in Western Europe, Eastern Europe, and Russia. The results generally validate the model.

While many areas of research in political science draw inferences from temporally aggregated data, rarely have researchers explored how temporal aggregation biases parameter estimates. With some notable exceptions (Freeman 1989, Political Analysis 1:61–98; Alt et al. 2001, Political Analysis 9:21–44; Thomas 2002, “Event Data Analysis and Threats from Temporal Aggregation”) political science studies largely ignore how temporal aggregation affects our inferences. This article expands upon others' work on this issue by assessing the effect of temporal aggregation decisions on vector autoregressive (VAR) parameter estimates, significance levels, Granger causality tests, and impulse response functions. While the study is relevant to all fields in political science, the results directly apply to event data studies of conflict and cooperation. The findings imply that political scientists should be wary of the impact that temporal aggregation has on statistical inference.