The uncovered set has frequently been proposed as a solution concept for majority rule settings. This paper tests this proposition using a new technique for estimating uncovered sets and a series of experiments, including five-player computer-mediated experiments and 35-player paper-format experiments. The results support the theoretic appeal of the uncovered set. Outcomes overwhelmingly lie in or near the uncovered set. Furthermore, when preferences shift, outcomes track the uncovered set. Although outcomes tend to occur within the uncovered set, they are not necessarily stable; majority dominance relationships still produce instability, albeit constrained by the uncovered set.

Linear regression models are frequently used to analyze distributive politics in the U.S. Congress; however, authors have used a variety of specifications with different implicit assumptions about how bicameralism shapes legislative bargaining. I derive a model that describes district or state spending authorizations as the aggregation of spending secured by multiple legislators working on behalf of overlapping constituencies. This bicameral shares model allows the disaggregation of House and Senate influence through simultaneous estimation of the relative bargaining power of the two chambers and the advantages that accrue to legislators holding partisan, committee, and other relevant affiliations. In the 2005 transportation bill, the model better predicts the functional form of small state advantage than recently employed specifications in the literature.

Text is arguably the most pervasive—and certainly the most persistent—artifact of political behavior. Extensive collections of texts with clearly recognizable political—as distinct from religious—content go back as far as 2500 BCE in the case of Mesopotamia and 1300 BCE for China, and 2400-year-old political discussions dating back to the likes of Plato, Aristotle, and Thucydides are common fare even in the introductory study of political thought. Political tracts were among the earliest productions following the introduction of low-cost printing in Europe—fueling more than a few revolutions and social upheavals—and continuous printed records of legislative debates, such as the British parliament's Hansard and precursors tracing to 1802, cover centuries of political discussion.

Private information characteristics like resolve and audience costs are powerful influences over strategic international behavior, especially crisis bargaining. As a consequence, states face asymmetric information when interacting with one another and will presumably try to learn about each others' private characteristics by observing each others' behavior. A satisfying statistical treatment would account for the existence of asymmetric information and model the learning process. This study develops a formal and statistical framework for incomplete information games that we term the Bayesian Quantal Response Equilibrium Model (BQRE model). Our BQRE model offers three advantages over existing work: it directly incorporates asymmetric information into the statistical model's structure, estimates the influence of private information characteristics on behavior, and mimics the temporal learning process that we believe takes place in international politics.

The study of bureaucracies and their relationship to political actors is central to understanding the policy process in the United States. Studying this aspect of American politics is difficult because theories of agency behavior, effectiveness, and control often require measures of administrative agencies' policy preferences, and appropriate measures are hard to find for a broad spectrum of agencies. We propose a method for measuring agency preferences based upon an expert survey of agency preferences for 82 executive agencies in existence between 1988 and 2005. We use a multirater item response model to provide a principled structure for combining subjective ratings based on scholarly and journalistic expertise with objective data on agency characteristics. We compare the resulting agency preference estimates and standard errors to existing alternative measures, discussing both the advantages and limitations of the method.

Wordscores is a widely used procedure for inferring policy positions, or scores, for new documents on the basis of scores for words derived from documents with known scores. It is computationally straightforward, requires no distributional assumptions, but has unresolved practical and theoretical problems. In applications, estimated document scores are on the wrong scale and the theoretical development does not specify a statistical model, so it is unclear what assumptions the method makes about political text and how to tell whether they fit particular text analysis applications. The first part of the paper demonstrates that badly scaled document score estimates reflect deeper problems with the method. The second part shows how to understand Wordscores as an approximation to correspondence analysis which itself approximates a statistical ideal point model for words. Problems with the method are identified with the conditions under which these layers of approximation fail to ensure consistent and unbiased estimation of the parameters of the ideal point model.

Analysts of cluster-randomized field experiments have an array of estimation techniques to choose from. Using Monte Carlo simulation, we evaluate the properties of point estimates and standard errors (SEs) generated by ordinary least squares (OLS) as applied to both individual-level and cluster-level data. We also compare OLS to alternative random effects estimators, such as generalized least squares (GLS). Our simulations assess efficiency across a variety of scenarios involving varying sample sizes and numbers of clusters. Our results confirm that conventional OLS SEs are severely biased downward and that, for all estimators, gains in efficiency come mainly from increasing the number of clusters, not increasing the number of individuals within clusters. We find relatively minor differences across alternative estimation approaches, but GLS seems to enjoy a slight edge in terms of the efficiency of its point estimates and the accuracy of its SEs. We illustrate the application of alternative estimation approaches using a clustered experiment in which Rock the Vote TV advertisements were used to encourage young voters in 85 cable TV markets to vote in the 2004 presidential election.

Increasingly, political science researchers are turning to Markov chain Monte Carlo methods to solve inferential problems with complex models and problematic data. This is an enormously powerful set of tools based on replacing difficult or impossible analytical work with simulated empirical draws from the distributions of interest. Although practitioners are generally aware of the importance of convergence of the Markov chain, many are not fully aware of the difficulties in fully assessing convergence across multiple dimensions. In most applied circumstances, every parameter dimension must be converged for the others to converge. The usual culprit is slow mixing of the Markov chain and therefore slow convergence towards the target distribution. This work demonstrates the partial convergence problem for the two dominant algorithms and illustrates these issues with empirical examples.

We present a simple method for estimating regressions based on recursive extensive-form games. Our procedure, which can be implemented in most standard statistical packages, involves sequentially estimating standard logits (or probits) in a manner analogous to backwards induction. We demonstrate that the technique produces consistent parameter estimates and show how to calculate consistent standard errors. To illustrate the method, we replicate Leblang's (2003) study of speculative attacks by financial markets and government responses to these attacks.

Entries in the burgeoning “text-as-data” movement are often accompanied by lists or visualizations of how word (or other lexical feature) usage differs across some pair or set of documents. These are intended either to establish some target semantic concept (like the content of partisan frames) to estimate word-specific measures that feed forward into another analysis (like locating parties in ideological space) or both. We discuss a variety of techniques for selecting words that capture partisan, or other, differences in political speech and for evaluating the relative importance of those words. We introduce and emphasize several new approaches based on Bayesian shrinkage and regularization. We illustrate the relative utility of these approaches with analyses of partisan, gender, and distributive speech in the U.S. Senate.

For many years, committee chairs have been selected on the basis of seniority. Recent work has suggested that alternative factors, specifically financial support of party goals and party unity, have diminished the importance of seniority in committee chair selection. However, previous work has either failed to quantify these effects or has done so with inappropriate methods. This paper argues for the use of a Bayesian conditional logit estimator to correctly model committee chair selection in the U.S. House of Representatives. Results show a declining commitment to seniority throughout the Republican era and support the importance of fundraising as a determinant of committee chair selection. This paper shows that two other factors, financial support of party goals and party unity, have essentially replaced seniority as the central criteria for selecting committee chairs.

This paper develops a procedure for locating proposals and legislators in a multidimensional policy space by applying agenda-constrained ideal point estimation. Placing proposals and legislators on the same scale allows an empirical test of the predictions of the spatial voting model. I illustrate this procedure by testing the predictive power of the uncovered set—a solution concept of the multidimensional spatial voting model—using roll call data from the U.S. Senate. Since empirical tests of the predictive power of the uncovered set have been limited to experimental data, this is the first empirical test of the concept's predictive power using real-world data.

Ecological inference is a statistical problem where aggregate-level data are used to make inferences about individual-level behavior. In this article, we conduct a theoretical and empirical study of Bayesian and likelihood inference for 2 × 2 ecological tables by applying the general statistical framework of incomplete data. We first show that the ecological inference problem can be decomposed into three factors: distributional effects, which address the possible misspecification of parametric modeling assumptions about the unknown distribution of missing data; contextual effects, which represent the possible correlation between missing data and observed variables; and aggregation effects, which are directly related to the loss of information caused by data aggregation. We then examine how these three factors affect inference and offer new statistical methods to address each of them. To deal with distributional effects, we propose a nonparametric Bayesian model based on a Dirichlet process prior, which relaxes common parametric assumptions. We also identify the statistical adjustments necessary to account for contextual effects. Finally, although little can be done to cope with aggregation effects, we offer a method to quantify the magnitude of such effects in order to formally assess its severity. We use simulated and real data sets to empirically investigate the consequences of these three factors and to evaluate the performance of our proposed methods. C code, along with an easy-to-use R interface, is publicly available for implementing our proposed methods (Imai, Lu, and Strauss, forthcoming).

In many applications of instrumental-variables regression, researchers seek to defend the plausibility of a key assumption: the instrumental variable is independent of the error term in a linear regression model. Although fulfilling this exogeneity criterion is necessary for a valid application of the instrumental-variables approach, it is not sufficient. In the regression context, the identification of causal effects depends not just on the exogeneity of the instrument but also on the validity of the underlying model. In this article, I focus on one feature of such models: the assumption that variation in the endogenous regressor that is related to the instrumental variable has the same effect as variation that is unrelated to the instrument. In many applications, this assumption may be quite strong, but relaxing it can limit our ability to estimate parameters of interest. After discussing two substantive examples, I develop analytic results (simulations are reported elsewhere). I also present a specification test that may be useful for determining the relevance of these issues in a given application.

In monetary policy, decision makers seek to influence the expectations of agents in ways that can avoid making abrupt, dramatic, and unexpected decisions. Yet in October 1979, Chairman Paul Volcker led the Federal Reserve's Federal Open Market Committee (FOMC) unanimously to shift its course in managing U.S. monetary policy, which in turn eventually brought the era of high inflation to an end. Although some analysts argue that “the presence and influence of one individual”—namely, Volcker—is sufficient to explain the policy shift, this overlooks an important feature of monetary policymaking. FOMC chairmen—however, omnipotent they may appear—do not act alone. They require the agreement of other committee members, and in the 1979 revolution, the decision was unanimous. How, then, did Chairman Volcker manage to bring a previously divided committee to a consensus in October 1979, and moreover, how did he retain the support of the committee throughout the following year in the face of mounting political and economic pressure against the Fed? We use automated content analysis to examine the discourse of the FOMC (with this discourse recorded in the verbatim transcripts of meetings). In applying this methodology, we assess the force of the arguments used by Chairman Volcker and find that deliberation in the FOMC did indeed “matter” both in 1979 and 1980. Specifically, Volcker led his colleagues in coming to understand and apply the idea of credible commitment in U.S. monetary policymaking.

Analysis of political communication is an important aspect of political research. Thematic content analysis has yielded considerable success both with manual and automatic coding, but Semantic Network Analysis has proven more difficult, both for humans and for the computer. This article presents a system for an automated Semantic Network Analysis of Dutch texts. The system automatically extracts relations between political actors based on the output of syntactic analysis of Dutch newspaper articles. Specifically, the system uses pattern matching to find source constructions and determine the semantic agent and patient of relations, and name matching and anaphora resolution to identify political actors. The performance of the system is judged by comparing the extracted relations to manual codings of the same material. Results on the level of measurement indicate acceptable performance. We also estimate performance at the levels of analysis by using a case study of media authority, resulting in good correlations between the theoretical variables derived from the automatic and manual analysis. Finally, we test a number of substantive hypotheses with regression models using the automatic and manual output, resulting in highly similar models in each case. This suggests that our method has sufficient performance to be used to answer relevant political questions in a valid way.

We measure legislative productivity for the entire history of the U.S. Congress. Current measures of legislative productivity are problematic because they measure productivity for a limited number of decades and because they are based on different aspects of productivity. We provide a methodology for measuring (1) a Legislative Productivity Index (LPI) and (2) a Major Legislation Index (MLI). We use the W-CALC algorithm of Stimson (1999, Public opinion in America: Moods, cycles, and swings. 2nd ed. Boulder, CO: Westview Press) to combine information from previously used indicators of productivity into measures of the LPI and the MLI. We provide examinations of content, convergent, and construct validity. The construct validity model includes potential determinants of legislative productivity. We conclude that the LPI and the MLI are superior measures of productivity than other measures used in the literature.

Although political methodologists are well aware of measurement issues and the problems that can be created, such concerns are not always front and center when we are doing substantive research. Here, we show how choices in measuring legislative preferences have influenced our understanding of what determines legislative outputs. Specifically, we replicate and extend Binder's highly influential analysis (Binder, Sarah A. 1999. The dynamics of legislative gridlock, 1947–96. American Political Science Review 93:519–33; see also Binder, Sarah A. 2003. Stalemate: Causes and consequences of legislative gridlock. Washington, DC: Brookings Institution) of legislative gridlock, which emphasizes how partisan, electoral, and institutional characteristics generate major legislative initiatives. Binder purports to show that examining the proportion, rather than the absolute number, of key policy proposals passed leads to the inference that these features, rather than divided government, are crucial for explaining gridlock. However, we demonstrate that this finding is undermined by flaws in preference measurement. Binder's results are a function of using W-NOMINATE scores never designed for comparing Senate to House members or for analyzing multiple Congresses jointly. When preferences are more appropriately measured with common space scores (Poole, Keith T. 1998. Recovering a basic space from a set of issue scales. American Journal of Political Science 42:964–93), there is no evidence that the factors that she highlights matter.

Models of ecological inference (EI) have to rely on crucial assumptions about the individual-level data-generating process, which cannot be tested because of the unavailability of these data. However, these assumptions may be violated by the unknown data and this may lead to serious bias of estimates and predictions. The amount of bias, however, cannot be assessed without information that is unavailable in typical applications of EI. We therefore construct a model that at least approximately accounts for the additional, nonsampling error that may result from possible bias incurred by an EI procedure, a model that builds on the Principle of Maximum Entropy. By means of a systematic simulation experiment, we examine the performance of prediction intervals based on this second-stage Maximum Entropy model. The results of this simulation study suggest that these prediction intervals are at least approximately correct if all possible configurations of the unknown data are taken into account. Finally, we apply our method to a real-world example, where we actually know the true values and are able to assess the performance of our method: the prediction of district-level percentages of split-ticket voting in the 1996 General Election of New Zealand. It turns out that in 95.5% of the New Zealand voting districts, the actual percentage of split-ticket votes lies inside the 95% prediction intervals constructed by our method.