In most situations of bilateral cooperation we can observe only whether or not potential partners actually cooperate. Yet we often want to know what factors lead the actors to enter into and continue cooperation. The model we develop—a dynamic version of bivariate probit with partial observability—permits one to estimate the probabilities that either of two parties would want to cooperate and to identify the factors that affect these probabilities. As an illustration, we focus on agreements between national governments and the International Monetary Fund. The model should have a wide applicability.

This paper discusses a nonstationary, heterogeneous Markov model designed to estimate entry and exit transition probabilities at the micro level from a time series of independent cross-sectional samples with a binary outcome variable. The model has its origins in the work of Moffitt and shares features with standard statistical methods for ecological inference. We outline the methodological framework proposed by Moffitt and present several extensions of the model to increase its potential application in a wider array of research contexts. We also discuss the relationship with previous lines of related research in political science. The example illustration uses survey data on American presidential vote intentions from a five-wave panel study conducted by Patterson in 1976. We treat the panel data as independent cross sections and compare the estimates of the Markov model with both dynamic panel parameter estimates and the actual observations in the panel. The results suggest that the proposed model provides a useful framework for the analysis of transitions in repeated cross sections. Open problems requiring further study are discussed.

At the heart of attitudinal and strategic explanations of judicial behavior is the assumption that justices have policy preferences. In this paper we employ Markov chain Monte Carlo methods to fit a Bayesian measurement model of ideal points for all justices serving on the U.S. Supreme Court from 1953 through 1999. We are particularly interested in determining to what extent ideal points of justices change throughout their tenure on the Court. This is important because judicial politics scholars oftentimes invoke preference measures that are time invariant. To investigate preference change, we posit a dynamic item response model that allows ideal points to change systematically over time. Additionally, we introduce Bayesian methods for fitting multivariate dynamic linear models to political scientists. Our results suggest that many justices do not have temporally constant ideal points. Moreover, our ideal point estimates outperform existing measures and explain judicial behavior quite well across civil rights, civil liberties, economics, and federalism cases.

Statistical models are often extended to explore the aggregate impact of policy reforms. After discussing these techniques and the incorporation of prediction uncertainty, this article examines the effects of registration reform in an analytic framework that explicitly considers the two stages that defined electoral participation throughout the 20th century in the United States—registration and then voting. Using selection bias techniques, the effects of counterfactual registration reform conditions are explored on the aggregate level of participation and the nature of representation in the electoral process. These offer a richer baseline of the impact of policy changes than previous work by directly exploring the expected level of dropoff in going to the polls by new registrants. Results indicate that the dropoff between registration and voting would be expected to increase as more individuals become registered. In addition, while turnout due to reforms among projected “new registrants” shows potentially larger biases than those among existing registrants, because of the different bases of registration the changes would still lead to a modest reduction in the disparity between actual group sizes and their role in elections.

Previous researchers have argued that necessary and/or sufficient causes should be tested through research designs that consider only cases with limited combinations of scores on the independent and the dependent variables. I explore the utility for causal inference of the design proposed by these authors, as compared to an “All Cases Design.” I find that, if researchers define the population carefully and appropriately, each case in the population contributes to causal inference and is therefore useful. Previous authors reject this claim on the basis of a view that holds constant the marginal distribution of either the dependent or the independent variable across the working and the alternate hypotheses. I argue that this restriction is not generally appropriate, and hence, an analysis that samples from the entire population is logically defensible. I also argue that this design is more statistically efficient. A reanalysis of two well-known studies demonstrates that sampling from all cases in the relevant population produces greater confidence in the hypothesis than sampling only from cases that experience the outcome.

The purpose of this Comment is to put the current debate regarding testing necessary conditions into perspective and to point out a particularly troubling aspect of the “all cases” research design (Seawright 2002).

Prior to the recent spate of books and articles in the social sciences (Ragin 1987; Dion 1988; Braumoeller and Goertz 2000), the debate over the testing or the confirmation of necessary conditions took place in the philosophical literature, mainly in terms of Hempel's (1945) paradox of the ravens. In what follows, I briefly review Hempel's paradox and the Bayesian solution to it. I argue that Seawright's account, while Bayesian in nature, relies on an assumption that no Bayesian would be willing to make.

In “Testing for Necessary and/or Sufficient Causation,” Jason Seawright (2002) presents an intriguing new Bayesian technique for testing theories that posit necessary conditions. His technique differs in substantial ways from those presented in separate articles by Dion (1998), Ragin (1987), and ourselves (2000) and constitutes a fundamental critique of those procedures. Having criticized quite a few procedures and theorists in our own article, we can hardly complain; rather, we recognize the constructive spirit of the endeavor and, in that same spirit, would like to offer a rejoinder.

The complex question of what counts as appropriate evidence for necessary and/or sufficient causation merits careful, ongoing discussion. I thank Kevin Clarke (2002) and Bear Braumoeller and Gary Goertz (2002) for their thoughtful responses to my (Seawright 2002) article, and I discuss their comments in turn.