“Robust standard errors” are used in a vast array of scholarship to correct standard errors for model misspecification. However, when misspecification is bad enough to make classical and robust standard errors diverge, assuming that it is nevertheless not so bad as to bias everything else requires considerable optimism. And even if the optimism is warranted, settling for a misspecified model, with or without robust standard errors, will still bias estimators of all but a few quantities of interest. The resulting cavernous gap between theory and practice suggests that considerable gains in applied statistics may be possible. We seek to help researchers realize these gains via a more productive way to understand and use robust standard errors; a new general and easier-to-use “generalized information matrix test” statistic that can formally assess misspecification (based on differences between robust and classical variance estimates); and practical illustrations via simulations and real examples from published research. How robust standard errors are used needs to change, but instead of jettisoning this popular tool we show how to use it to provide effective clues about model misspecification, likely biases, and a guide to considerably more reliable, and defensible, inferences. Accompanying this article is software that implements the methods we describe.

The list experiment, also known as the item count technique, is becoming increasingly popular as a survey methodology for eliciting truthful responses to sensitive questions. Recently, multivariate regression techniques have been developed to predict the unobserved response to sensitive questions using respondent characteristics. Nevertheless, no method exists for using this predicted response as an explanatory variable in another regression model. We address this gap by first improving the performance of a naive two-step estimator. Despite its simplicity, this improved two-step estimator can only be applied to linear models and is statistically inefficient. We therefore develop a maximum likelihood estimator that is fully efficient and applicable to a wide range of models. We use a simulation study to evaluate the empirical performance of the proposed methods. We also apply them to the Mexico 2012 Panel Study and examine whether vote-buying is associated with increased turnout and candidate approval. The proposed methods are implemented in open-source software.

Over the past eight decades, millions of people have been surveyed on their political opinions. Until recently, however, polls rarely included enough questions in a given domain to apply scaling techniques such as IRT models at the individual level, preventing scholars from taking full advantage of historical survey data. To address this problem, we develop a Bayesian group-level IRT approach that models latent traits at the level of demographic and/or geographic groups rather than individuals. We use a hierarchical model to borrow strength cross-sectionally and dynamic linear models to do so across time. The group-level estimates can be weighted to generate estimates for geographic units. This framework opens up vast new areas of research on historical public opinion, especially at the subnational level. We illustrate this potential by estimating the average policy liberalism of citizens in each U.S. state in each year between 1972 and 2012.

Questions about racial or ethnic group identity feature centrally in many social science theories, but detailed data on ethnic composition are often difficult to obtain, out of date, or otherwise unavailable. The proliferation of publicly available geocoded person names provides one potential source of such data'if researchers can effectively link names and group identity. This article examines that linkage and presents a methodology for estimating local ethnic or racial composition using the relationship between group membership and person names. Common approaches for linking names and identity groups perform poorly when estimating group proportions. I have developed a new method for estimating racial or ethnic composition from names which requires no classification of individual names. This method provides more accurate estimates than the standard approach and works in any context where person names contain information about group membership. Illustrations from two very different contexts are provided: the United States and the Republic of Kenya.

Electoral rules have the potential to affect the size and composition of the voting public. Yet scholars disagree over whether requiring voters to register well in advance of Election Day reduces turnout. We present a new approach, using web searches for “voter registration” to measure interest in registering, both before and after registration deadlines for the 2012 U.S. presidential election. Many Americans sought information on “voter registration” even after the deadline in their state had passed. Combining web search data with evidence on the timing of registration for 80 million Americans, we model the relationship between search and registration. Extrapolating this relationship to the post-deadline period, we estimate that an additional 3–4 million Americans would have registered in time to vote, if deadlines had been extended to Election Day. We test our approach by predicting out of sample and with historical data. Web search data provide new opportunities to measure and study information-seeking behavior.

Electoral competitiveness is a key explanatory construct across a broad swath of phenomena, finding application in diverse areas related to political incentives and behavior. Despite its frequent theoretical use, no valid measure of electoral competitiveness exists that applies across different electoral and party systems. We argue that one particular type of electoral competitiveness'electoral risk'can be estimated across institutional contexts and matters most for incumbent behavior. We propose, estimate, and make available a cross-nationally applicable measure for elections in 22 developed democracies between 1960 and 2011. Unlike extant alternatives, our measure captures vote volatility and is constructed at the party (not system) level, exogenous to most policy predictors, and congruent with the perceptions and incentives of policy-makers.

Recent advances in research tools for the systematic analysis of textual data are enabling exciting new research throughout the social sciences. For comparative politics, scholars who are often interested in non-English and possibly multilingual textual datasets, these advances may be difficult to access. This article discusses practical issues that arise in the processing, management, translation, and analysis of textual data with a particular focus on how procedures differ across languages. These procedures are combined in two applied examples of automated text analysis using the recently introduced Structural Topic Model. We also show how the model can be used to analyze data that have been translated into a single language via machine translation tools. All the methods we describe here are implemented in open-source software packages available from the authors.

Many types of time series data in political science, including polling data and events data, exhibit important features'such as irregular spacing, noninstantaneous observation, overlapping observation times, and sampling or other measurement error'that are ignored in most statistical analyses because of model limitations. Ignoring these properties can lead not only to biased coefficients but also to incorrect inference about the direction of causality. This article develops a continuous-time model to overcome these limitations. This new model treats observations as noisy samples collected over an interval of time and can be viewed as a generalization of the vector autoregressive model. Monte Carlo simulations and two empirical examples demonstrate the importance of modeling these features of the data.

In November 2010, the WikiLeaks organization began the release of over 250,000 diplomatic cables sent by U.S. embassies to the U.S. State Department, uploaded to its website by (then) Private Manning, an intelligence analyst with the U.S. Army. This leak was widely condemned, including by then Secretary of State Hillary Clinton. We assess the severity of the leak by considering the size of the disclosure relative to all diplomatic cables that were in existence at the time—a quantity that is not known outside official sources. We rely on the fact that the cables that were leaked are internally indexed in such a way that they may be treated as a sample from a discrete uniform distribution with unknown maximum; this is a version of the well-known “German Tank Problem.” We consider three estimators that rely on discrete uniformity—maximum likelihood, Bayesian, and frequentist unbiased minimum variance—and demonstrate that the results are very similar in all cases. To supplement these estimators, we employ a regression-based procedure that incorporates the timing of cables' release in addition to their observed serial numbers. We estimate that, overall, approximately 5% of all cables from this timeframe were leaked, but that this number varies considerably at the embassy-year level. Our work provides a useful characterization of the sample of documents available to international relations scholars interested in testing theories of “private information,” while helping inform the public debate surrounding Manning's trial and 35-year prison sentence.

The accuracy of published findings is compromised when researchers fail to report and adjust for multiple testing. Preregistration of studies and the requirement of preanalysis plans for publication are two proposed solutions to combat this problem. Some have raised concerns that such changes in research practice may hinder inductive learning. However, without knowing the extent of underreporting, it is difficult to assess the costs and benefits of institutional reforms. This paper examines published survey experiments conducted as part of the Time-sharing Experiments in the Social Sciences program, where the questionnaires are made publicly available, allowing us to compare planned design features against what is reported in published research. We find that: (1) 30% of papers report fewer experimental conditions in the published paper than in the questionnaire; (2) roughly 60% of papers report fewer outcome variables than what are listed in the questionnaire; and (3) about 80% of papers fail to report all experimental conditions and outcomes. These findings suggest that published statistical tests understate the probability of type I errors.