A wide range of potentially useful data are available for election forecasting: the results of previous elections, a multitude of preelection polls, and predictors such as measures of national and statewide economic performance. How accurate are different forecasts? We estimate predictive uncertainty via analysis of data collected from past elections (actual outcomes, preelection polls, and model estimates). With these estimated uncertainties, we use Bayesian inference to integrate the various sources of data to form posterior distributions for the state and national two-party Democratic vote shares for the 2008 election. Our key idea is to separately forecast the national popular vote shares and the relative positions of the states. More generally, such an approach could be applied to study changes in public opinion and other phenomena with wide national swings and fairly stable spatial distributions relative to the national average.

Although estimating the revealed preferences of members of Congress is straightforward, estimating the position of the president relative to Congress is not. Current estimates place the president as considerably more ideologically extreme than one would expect. These estimates, however, are very sensitive to the set of presidential positions used in the roll call analyses for the 103rd through 109th Congresses. The president often obtains more moderate ideal point estimates relative to Congress when including positions based on signing bills into law.

Both qualitative and quantitative research routinely fall short, producing misleading causal inferences. Because these weaknesses are in part different, we are convinced that multimethod strategies are productive. Each approach can provide additional leverage that helps address shortcomings of the other. This position is quite distinct from that of Beck, who believes that the two types of analysis cannot be adjoined. We review examples of adjoining that Beck dismisses, based on what we see as his outdated view of qualitative methods. By contrast, we show that these examples demonstrate how qualitative and quantitative analysis can work together.

The polity2 variable from the Polity IV project is the most popular measure of a country's political regime. This article contends that the coding rules employed to create a polity2 score during years of so-called interregnum and affected transitions produce a measure of democracy that lacks face validity. Using both single and multiple imputation methods, we construct and evaluate several variables that offer alternative measures to polity2 during such periods. We recommend that scholars using polity2 test whether their results are robust to using our alternatives and using multiple imputation techniques instead. Where robustness cannot be established, scholars need to theoretically justify the choice of either polity2 or one of the alternatives.

This study presents a survey-based method for conducting inference into the determinants of sensitive political behavior. The approach combines two well-established literatures in statistical methods in the social sciences: the randomized response (RR) methodology utilized to reduce evasive answer bias and the generalized propensity score methodology utilized to draw inferences about causal effects in observational studies. The approach permits one to estimate the causal impact of a multivalued predictor variable of interest on a given sensitive behavior in the face of unknown interaction effects between the predictor and the confounders as well as nonlinearities in the relationship between the confounders and the sensitive behavior. Simulation results point to the superior performance of the RR relative to direct survey questioning using this method for samples of moderate to large size. The utility of the approach is illustrated through an application to corruption in the public bureaucracy in three countries in South America.

This paper extends the Calculus of Voting of McKelvey and Ordeshook, providing the first direct derivation of the conditions under which voters will vote strategically: choose their second-most preferred candidate in order to prevent their least-preferred candidate from winning. Addressing this theoretical problem is important, as nearly all empirical research on strategic voting either implicitly or explicitly tests hypotheses which originate from this seminal model. The formal result allows us to isolate the subset of voters to which strategic voting hypotheses properly apply and in turn motivates a critical reevaluation of past empirical work. In making this argument, we develop a unified and parsimonious framework for understanding competing models of tactical voter choice. The typology helps to elucidate the methodological difficulties in studying tactical behavior when faced with heterogeneous explanatory models and suggests the need for both theoretical caution and more precise data instruments in future empirical work.

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 fragile model specifications, and leads to the estimation of bloated models with too many control variables. Bayesian model averaging (BMA) offers a systematic method for analyzing specification uncertainty and checking the robustness of one's results to alternative model specifications, but it has not come into wide usage within the discipline. In this paper, we introduce important recent developments in BMA and show how they enable a different approach to using the technique in applied social science research. We illustrate the methodology by reanalyzing data from three recent studies using BMA software we have modified to respect statistical conventions within political science.

Signaling models are ubiquitous in political science. An essential characteristic of these models is that actors can update their beliefs about their opponents. An actor observes the behavior of his opponent, and this behavior functions as a signal that allows the actor to learn more about his opponent's true “type.” As a result, the actor is able to adapt his own behavior. Current statistical models of strategic choice based on perfect Bayesian equilibrium, however, allow for very little, if any, belief updating. I explain why current models allow for little updating and offer in their stead a new, fully strategic choice estimator that calculates the correct amount of belief updating.