This special issue is devoted to original articles that reflect recent progress in one of the most exciting developments in Political Science, the National Science Foundation's (NSF) initiative called Empirical Implications of Theoretical Models (EITM). This initiative reflects the ideas and hard work of the Political Science team there, Jim Granato and Frank Scioli, backed up by the contributions of an EITM panel that assembled at NSF in July 2001, some of whose observations we mention below. The challenge set by the EITM program is straightforward: to improve our theoretical work so that it yields more testable hypotheses and to improve our methodological work so that testing is made more effective and informative about theories. It is hard to object to this, but it also turns out to be hard to meet fully. The EITM initiative contains several components designed to close the gap between theoretical derivation and empirical test. This issue represents one component, presenting some of the most innovative work in the discipline on the current research frontier in EITM.

Social scientists are often confronted with theories in which one or more actors make choices over a discrete set of options. In this article, I generalize a broad class of statistical discrete choice models, with both well-known and new nonstrategic and strategic special cases. I demonstrate how to derive statistical models from theoretical discrete choice models and, in doing so, I address the statistical implications of three sources of uncertainty: agent error, private information about payoffs, and regressor error. For strategic and some nonstrategic choice models, the three types of uncertainty produce different statistical models. In these cases, misspecifying the type of uncertainty leads to biased and inconsistent estimates, and to incorrect inferences based on estimated probabilities.

We develop an empirical estimator directly from an extensive-form crisis bargaining game with incomplete information and discuss its features and limitations. The estimator makes it possible to draw inferences about states' payoffs from observational data on crisis outcomes while remaining faithful to the theorized strategic and informational structure. We compare this estimator to one based on a symmetric information version of the same game, using the quantal response equilibrium proposed in this context by Signorino (1999, American Political Science Review 93:279–298). We then address issues of identification that arise in trying to learn about actors' utilities by observing their play of a strategic game. In general, a number of identifying restrictions are needed in order to pin down the distribution of payoffs and the effects of covariates on those payoffs.

In recent work, Signorino (American Political Science Review 93:279–297, 1999; International Interactions 28:93–115, 2002) has sought to test statistical models derived from extensive-form games in the context of international relations research focusing on conflict and interstate bargaining. When two or more actors interact with one another under conditions of uncertainty, Signorino demonstrates that it is necessary to incorporate such strategic interaction into the underlying model to avoid potential threats to statistical inference. Outside the realm of international relations research, however, there have been limited applications of Signorino's strategic probit model in understanding strategic interaction. In this article, I present an empirical comparison of probit and strategic probit models in the context of candidate competition in House elections during the 1990s. I show that incumbent spending deters challenger entry and factors such as minority party affiliation and redistricting significantly affect incumbent career decisions, findings that run counter to those reported in the nonstrategic model. Overall, the results illustrate that failing to account for strategic interaction can lead to biased and inaccurate estimates related to challenger and incumbent entry decisions.

Scholars of legislative studies typically use ideal point estimates from scaling procedures to test theories of legislative politics. We contend that theory and methods may be better integrated by directly incorporating maintained and to be tested hypotheses in the statistical model used to estimate legislator preferences. In this view of theory and estimation, formal modeling (1) provides auxiliary assumptions that serve as constraints in the estimation process, and (2) generates testable predictions. The estimation and hypothesis testing procedure uses roll call data to evaluate the validity of theoretically derived to be tested hypotheses in a world where maintained hypotheses are presumed true. We articulate the approach using the language of statistical inference (both frequentist and Bayesian). The approach is demonstrated in analyses of the well-studied Powell amendment to the federal aid-to-education bill in the 84th House and the Compromise of 1790 in the 1st House.

Those interested in political phenomena such as voting have found random utility models, originally developed for decisions such as transportation choice, especially attractive, as the underlying model can yield a statistical model with a few simple, realistic assumptions. Unfortunately, such models have proven difficult to apply to situations with more than two votes and three alternatives or an unknown cutpoint. Additionally, as we show, standard applications of such models to voting, while producing consistent parameter estimates, yield standard errors that are too small and, due to a failure to employ all relevant theoretical information, biased ideal point estimates. We specify a general model applicable to any number of votes and alternatives, with correct standard errors and unbiased ideal point estimates. We apply this model to a number of cases studied by previous scholars involving legislative voting over the minimum wage: (1) when there are two votes and two known cutpoints (K. Krehbiel and D. Rivers, American Journal of Political Science, 1988, 32, 1151–1174); (2) when there are three votes and three known cutpoints (J. Wilkerson, American Journal of Political Science, 1991, 35, 613–623); and (3) when there are three votes but where one cutpoint is unknown given a lack of knowledge about the impact of a policy (J. Wilkerson, American Journal of Political Science, 1991, 35, 613–623) or the possibility of sophisticated voting (C. Volden, Journal of Politics, 1998, 60, 149–173). We show that in various contexts our analysis improves on existing methods, yielding consistent and efficient ideal point estimates and a better-fitting model with improved predictive accuracy.

We develop a model of legislative policymaking in which individual legislators are concerned with both policy and reelection. Legislators' preferences are private information, and they have two means of communicating their preferences to voters. First, they each have a “party label” that credibly identifies an interval within which their ideal points must lie. Second, their roll call votes may convey additional information about their preferences. Each legislator must therefore tailor his or her votes to his or her district in order to forestall a reelection challenge from the opposing party. In equilibrium, nonsincere voting records will occur mostly in moderate districts, where extreme incumbents are vulnerable to challenges from relatively centrist candidates. In those districts, the most extreme legislators may even choose to vote sincerely and retire rather than compile a moderate voting record. Thus, both roll call scores and candidate types will be responsive to district type. An empirical test of shifts in roll call scores of retiring House members in moderate districts confirms these findings.

The causal arguments of modern, positive political science often imply complex interactions among multiple explanatory factors. In one example from comparative and international political economy (C&IPE), sharing of monetary-policymaking control between partially autonomous central banks and politically responsive governments yields inflation as a convex combination of the rates that would have held under full-government and full-central-bank policy control. The anti-inflationary effect of central bank independence (autonomy plus conservatism: CBA) therefore depends on all political—economic variables to which central banks and governments respond differently, and, vice versa, CBA mutes the inflation effects of all such factors. Extending that logic of shared policy control to open political economies: insofar as domestic monetary authorities fix exchange rates, they effectively delegate inflation control to foreign (peg-currency) authorities, and policymakers in small and financially exposed economies must match domestic inflation to foreign (global) rates to avoid massive exchange-rate pressures. Thus, analogously, the domestic-inflation effects of fixed exchange rates and of monetary exposure depend on each other and on many other institutional and structural aspects of the domestic and foreign political economies, and, vice versa, the effects of all domestic and foreign political—economic conditions depend on degrees of exchange-rate fixity and financial openness at home and abroad. This article shows how to model such complexly interactive hypotheses empirically compactly and substantively meaningfully, and demonstrates the postwar inflation records of 21 developed democracies to favor such specifications decidedly over standard linear-additive or linear-interactive alternatives. The concluding sections discuss specific results and implications and then suggest several more potential applications of this general approach to further instances of shared policy control and other substantive contexts that induce the multiple, complex interactions characteristic of modern, positive political science in general and C&IPE especially.