Spatial econometric models become increasingly popular in various subfields of political science. However, the necessity to specify the underlying network of dependencies, denoted by $\boldsymbol{W}$, prior to estimation is a prevalent source of criticism since the true dependence structure is rarely known and theories mostly provide insufficient guidance. The present study investigates the effects of this network uncertainty which is a special case of model uncertainty that arises from uncertainty about the correct specification of $\boldsymbol{W}$. It advocates Bayesian model averaging (BMA) as a superior approach to this problem, located at the intersection of theory and empirics. Conducting Monte Carlo experiments, I demonstrate that, while the effect estimates are robust toward a misspecification in the functional form of $\boldsymbol{W}$, uncertainty in the neighborhood definition can bias the effect estimates derived from spatial autoregressive models. In contrast to alternative techniques, BMA directly addresses network uncertainty, correctly identifies the true network structure in the set of feasible alternatives, and provides unbiased effect estimates. Two replication studies from different subfields of the discipline illustrate the benefits of this approach for applied research.

Empirical applications of the spatial theory of elections typically rely on the discrete choice framework to arrive at probabilistic voting models. Whereas in the classic model voter choice is solely a function of spatial proximity, neo-Downsian models also incorporate voter-specific nonpolicy attributes, which are represented by sociodemographic characteristics. One prominent line of such probabilistic models, Schofield’s Valence Model, additionally includes party valences into voter utility functions. The model rests on the estimated party intercepts to measure the valence advantages empirically. The party intercepts are ordered based on their values, and then this valence ranking is used further to predict equilibrium locations. The paper demonstrates that this measurement strategy does not provide unique results in fully specified models due to central properties of discrete choice models and the specific nature of party intercepts in these models. Drawing on a simple example based on mass election surveys from Germany, it is shown that the valence ranking, the crucial factor to investigate how valence differences affect the nature of spatial competition, is highly sensitive to arbitrary coding decisions. As a consequence, it is impossible to represent valence with the constants and to infer something substantial from the resulting valence ranking.

In political science, data with heterogeneous units are used in many studies, such as those involving legislative proposals in different policy areas, electoral choices by different types of voters, and government formation in varying party systems. To disentangle decision-making mechanisms by units, traditional discrete choice models focus exclusively on the conditional mean and ignore the heterogeneous effects within a population. This paper proposes a conditional binary quantile model that goes beyond this limitation to analyze discrete response data with varying alternative-specific features. This model offers an in-depth understanding of the relationship between the explanatory and response variables. Compared to conditional mean-based models, the conditional binary quantile model relies on weak distributional assumptions and is more robust to distributional misspecification. The model also relaxes the assumption of the independence of irrelevant alternatives, which is often violated in practice. The method is applied to a range of political studies to show the heterogeneous effects of explanatory variables across the conditional distribution. Substantive interpretations from counterfactual scenarios are used to illustrate how the conditional binary quantile model captures unobserved heterogeneity, which extant models fail to do. The results point to the risk of averaging out the heterogeneous effects across units by conditional mean-based models.

Matching for causal inference is a well-studied problem, but standard methods fail when the units to match are text documents: the high-dimensional and rich nature of the data renders exact matching infeasible, causes propensity scores to produce incomparable matches, and makes assessing match quality difficult. In this paper, we characterize a framework for matching text documents that decomposes existing methods into (1) the choice of text representation and (2) the choice of distance metric. We investigate how different choices within this framework affect both the quantity and quality of matches identified through a systematic multifactor evaluation experiment using human subjects. Altogether, we evaluate over 100 unique text-matching methods along with 5 comparison methods taken from the literature. Our experimental results identify methods that generate matches with higher subjective match quality than current state-of-the-art techniques. We enhance the precision of these results by developing a predictive model to estimate the match quality of pairs of text documents as a function of our various distance scores. This model, which we find successfully mimics human judgment, also allows for approximate and unsupervised evaluation of new procedures in our context. We then employ the identified best method to illustrate the utility of text matching in two applications. First, we engage with a substantive debate in the study of media bias by using text matching to control for topic selection when comparing news articles from thirteen news sources. We then show how conditioning on text data leads to more precise causal inferences in an observational study examining the effects of a medical intervention.

Classical generalized linear models assume that marginal effects are homogeneous in the population given the observed covariates. Researchers can never be sure a priori if that assumption is adequate. Recent literature in statistics and political science have proposed models that use Dirichlet process priors to deal with the possibility of latent heterogeneity in the covariate effects. In this paper, we extend and generalize those approaches and propose a hierarchical Dirichlet process of generalized linear models in which the latent heterogeneity can depend on context-level features. Such a model is important in comparative analyses when the data comes from different countries and the latent heterogeneity can be a function of country-level features. We provide a Gibbs sampler for the general model, a special Gibbs sampler for gaussian outcome variables, and a Hamiltonian Monte Carlo within Gibbs to handle discrete outcome variables. We demonstrate the importance of accounting for latent heterogeneity with a Monte Carlo exercise and with two applications that replicate recent scholarly work. We show how Simpson’s paradox can emerge in the empirical analysis if latent heterogeneity is ignored and how the proposed model can be used to estimate heterogeneity in the effect of covariates.

The use of cluster robust standard errors (CRSE) is common as data are often collected from units, such as cities, states or countries, with multiple observations per unit. There is considerable discussion of how best to estimate standard errors and confidence intervals when using CRSE (Harden 2011; Imbens and Kolesár 2016; MacKinnon and Webb 2017; Esarey and Menger 2019). Extensive simulations in this literature and here show that CRSE seriously underestimate coefficient standard errors and their associated confidence intervals, particularly with a small number of clusters and when there is little within cluster variation in the explanatory variables. These same simulations show that a method developed here provides more reliable estimates of coefficient standard errors. They underestimate confidence intervals for tests of individual and sets of coefficients in extreme conditions, but by far less than do CRSE. Simulations also show that this method produces more accurate standard error and confidence interval estimates than bootstrapping, which is often recommended as an alternative to CRSE.

This article offers a description and discussion of “shadowing” as a data collection and analytic tool, highlighting potential research opportunities related to the direct observation of individuals—principally political elites—in their normal daily routine for an extended period of time, often between one day and one week. In contrast with large-scale data collection methods, including surveys, shadowing enables researchers to develop detailed observations of political behavior that are not limited by the availability of administrative data or the constraints of a questionnaire or an interview guide. Unlike more in-depth qualitative methods, such as ethnography, shadowing is scalable in a manner that allows for larger sample sizes and the potential for medium-N inference. I provide a detailed account of how to design and conduct a shadowing study, including sampling strategies, techniques for coding shadowing data, and processes for drawing inferences about the behavior of shadowed subjects, drawing on examples from a completed shadowing-based study. I also discuss ways to mitigate selection and observer biases, presenting results that suggest these can be no more pronounced when shadowing political elites than in other forms of observational research.

The concept of electoral competition plays a central role in many subfields of political science, but no consensus exists on how to measure it. One key challenge is how to conceptualize and measure electoral competitiveness at the district level across alternative electoral systems. Recent efforts to meet this challenge have introduced general measures of competitiveness which rest on explicit calculations about how votes translate into seats, but also implicit assumptions about how effort maps into votes (and how costly effort is). We investigate how assumptions about the effort-to-votes mapping affect the units in which competitiveness is best measured, arguing in favor of vote-share-denominated measures and against vote-share-per-seat measures. Whether elections under multimember proportional representation systems are judged more or less competitive than single-member plurality or runoff elections depends directly on the units in which competitiveness is assessed (and hence on assumptions about how effort maps into votes).

An increasing number of studies exploit the occurrence of unexpected events during the fieldwork of public opinion surveys to estimate causal effects. In this paper, we discuss the use of this identification strategy based on unforeseen and salient events that split the sample of respondents into treatment and control groups: the Unexpected Event during Survey Design. In particular, we focus on the assumptions under which unexpected events can be exploited to estimate causal effects and we discuss potential threats to identification, paying especial attention to the observable and testable implications of these assumptions. We propose a series of best practices in the form of various estimation strategies and robustness checks that can be used to lend credibility to the causal estimates. Drawing on data from the European Social Survey, we illustrate the discussion of this method with an original study of the impact of the Charlie Hebdo terrorist attacks (Paris, 01/07/2015) on French citizens’ satisfaction with their national government.

When making causal inferences, post-treatment confounders complicate analyses of time-varying treatment effects. Conditioning on these variables naively to estimate marginal effects may inappropriately block causal pathways and may induce spurious associations between treatment and the outcome, leading to bias. To avoid such bias, researchers often use marginal structural models (MSMs) with inverse probability weighting (IPW). However, IPW requires models for the conditional distributions of treatment and is highly sensitive to their misspecification. Moreover, IPW is relatively inefficient, susceptible to finite-sample bias, and difficult to use with continuous treatments. We introduce an alternative method of constructing weights for MSMs, which we call “residual balancing”. In contrast to IPW, it requires modeling the conditional means of the post-treatment confounders rather than the conditional distributions of treatment, and it is therefore easier to use with continuous treatments. Numeric simulations suggest that residual balancing is both more efficient and more robust to model misspecification than IPW and its variants in a variety of scenarios. We illustrate the method by estimating (a) the cumulative effect of negative advertising on election outcomes and (b) the controlled direct effect of shared democracy on public support for war. Open-source software is available for implementing the proposed method.

Information about the ideological positions of different political actors is crucial in answering questions regarding political representation, polarization, and voting behavior. One way to obtain such information is to ask survey respondents to place actors on a common ideological scale, but, unfortunately, respondents typically display a set of biases when performing such placements. Key among these are rationalization bias and differential item functioning (DIF). While Aldrich–McKelvey (AM) scaling offers a useful solution to DIF, it ignores the issue of rationalization bias, and this study presents Monte Carlo simulations demonstrating that AM-type models thus can give inaccurate results. As a response to this challenge, this study develops an alternative Bayesian scaling approach, which simultaneously estimates DIF and rationalization bias, and therefore performs better when the latter bias is present.

When do parties respond to their political rivals and when do they ignore them? This article presents a new computational framework to detect, analyze and predict partisan responsiveness by showing when parties on opposite poles of the political spectrum react to each other’s agendas and thereby contribute to polarization. Once spikes in responsiveness are detected and categorized using latent Dirichlet allocation, we utilize the terms that comprise the topics, together with a gradient descent solver, to assess the classifier’s predictive accuracy. Using 10,597 documents from the official websites of radical right and ethnic political parties in Slovakia (2004–2014), the analysis predicts which political issues will elicit partisan reactions, and which will be ignored, with an accuracy of 83% (F-measure) and outperforms both Random Forest and Naive Bayes classifiers. Subject matter experts validate the approach and interpret the results.

Electoral boundaries are an integral part of election administration. District boundaries delineate which legislative election voters are eligible to participate in, and precinct boundaries identify, in many localities, where voters cast in-person ballots on Election Day. Election officials are tasked with resolving a tremendously large number of intersections of registered voters with overlapping electoral boundaries. Any large-scale data project is susceptible to errors, and this task is no exception. In two recent close elections, these errors were consequential to the outcome. To address this problem, we describe a method to audit the assignment of registered voters to districts. We apply the methodology to Florida’s voter registration file to identify thousands of registered voters assigned to the wrong state House district, many of which local election officials have verified and rectified. We discuss how election officials can best use this technique to detect registered voters assigned to the wrong electoral boundary.

Conjoint analysis is a common tool for studying political preferences. The method disentangles patterns in respondents’ favorability toward complex, multidimensional objects, such as candidates or policies. Most conjoints rely upon a fully randomized design to generate average marginal component effects (AMCEs). They measure the degree to which a given value of a conjoint profile feature increases, or decreases, respondents’ support for the overall profile relative to a baseline, averaging across all respondents and other features. While the AMCE has a clear causal interpretation (about the effect of features), most published conjoint analyses also use AMCEs to describe levels of favorability. This often means comparing AMCEs among respondent subgroups. We show that using conditional AMCEs to describe the degree of subgroup agreement can be misleading as regression interactions are sensitive to the reference category used in the analysis. This leads to inferences about subgroup differences in preferences that have arbitrary sign, size, and significance. We demonstrate the problem using examples drawn from published articles and provide suggestions for improved reporting and interpretation using marginal means and an omnibus F-test. Given the accelerating use of these designs in political science, we offer advice for best practice in analysis and presentation of results.

Ecological inference (EI) is the process of learning about individual behavior from aggregate data. We relax assumptions by allowing for “linear contextual effects,” which previous works have regarded as plausible but avoided due to nonidentification, a problem we sidestep by deriving bounds instead of point estimates. In this way, we offer a conceptual framework to improve on the Duncan–Davis bound, derived more than 65 years ago. To study the effectiveness of our approach, we collect and analyze 8,430 $2\times 2$ EI datasets with known ground truth from several sources—thus bringing considerably more data to bear on the problem than the existing dozen or so datasets available in the literature for evaluating EI estimators. For the 88% of real data sets in our collection that fit a proposed rule, our approach reduces the width of the Duncan–Davis bound, on average, by about 44%, while still capturing the true district-level parameter about 99% of the time. The remaining 12% revert to the Duncan–Davis bound.

Declining telephone response rates have forced several transformations in survey methodology, including cell phone supplements, nonprobability sampling, and increased reliance on model-based inferences. At the same time, advances in statistical methods and vast amounts of new data sources suggest that new methods can combat some of these problems. We focus on one type of data source—voter registration databases—and show how they can improve inferences from political surveys. These databases allow survey methodologists to leverage political variables, such as party registration and past voting behavior, at a large scale and free of overreporting bias or endogeneity between survey responses. We develop a general process to take advantage of this data, which is illustrated through an example where we use multilevel regression and poststratification to produce vote choice estimates for the 2012 presidential election, projecting those estimates to 195 million registered voters in a postelection context. Our inferences are stable and reasonable down to demographic subgroups within small geographies and even down to the county or congressional district level. They can be used to supplement exit polls, which have become increasingly problematic and are not available in all geographies. We discuss problems, limitations, and open areas of research.

Experiments often include multiple treatments, with the primary goal to compare the causal effects of those treatments. This study focuses on comparing the causal anatomies of multiple treatments through the use of causal mediation analysis. It proposes a novel set of comparative causal mediation (CCM) estimands that compare the mediation effects of different treatments via a common mediator. Further, it derives the properties of a set of estimators for the CCM estimands and shows these estimators to be consistent (or conservative) under assumptions that do not require the absence of unobserved confounding of the mediator–outcome relationship, which is a strong and nonrefutable assumption that must typically be made for consistent estimation of individual causal mediation effects. To illustrate the method, the study presents an original application investigating whether and how the international legal status of a foreign policy commitment can increase the domestic political “audience costs” that democratic governments suffer for violating such a commitment. The results provide novel evidence that international legalization can enhance audience costs via multiple causal channels, including by amplifying the perceived immorality of violating the commitment.

Word vectorization is an emerging text-as-data method that shows great promise for automating the analysis of semantics—here, the cultural meanings of words—in large volumes of text. Yet successes with this method have largely been confined to massive corpora where the meanings of words are presumed to be fixed. In political science applications, however, many corpora are comparatively small and many interesting questions hinge on the recognition that meaning changes over time. Together, these two facts raise vexing methodological challenges. Can word vectors trace the changing cultural meanings of words in typical small corpora use cases? I test four time-sensitive implementations of word vectors (word2vec) against a gold standard developed from a modest data set of 161 years of newspaper coverage. I find that one implementation method clearly outperforms the others in matching human assessments of how public dialogues around equality in America have changed over time. In addition, I suggest best practices for using word2vec to study small corpora for time series questions, including bootstrap resampling of documents and pretraining of vectors. I close by showing that word2vec allows granular analysis of the changing meaning of words, an advance over other common text-as-data methods for semantic research questions.

After seeking a “manageable standard” to apply to claims of partisan gerrymandering for over three decades, the Supreme Court has finally given up the chase, ruling that such claims are nonjusticiable. What is to be done? An extended history of successful congressional action suggests that the legislative pathway is more practical than often believed. Statutory requirements also make it possible to consider a broader suite of districting objectives. This paper presents a flexible new software and a framework for evaluating the practical implications of explicit objectives. I apply this approach to the conditions last required by Congress, generating equipopulous, contiguous, and compact districts. Among these conditions, the formal definition of compactness has proven contentious. Does it matter? I contrast the representation of the political parties and of racial and ethnic minorities under plans optimized according to 18 different definitions of compactness. On these grounds, the definitions are markedly consistent. These methods may be extended to alternative districting objectives and criteria.

Supervised machine learning methods are increasingly employed in political science. Such models require costly manual labeling of documents. In this paper, we introduce active learning, a framework in which data to be labeled by human coders are not chosen at random but rather targeted in such a way that the required amount of data to train a machine learning model can be minimized. We study the benefits of active learning using text data examples. We perform simulation studies that illustrate conditions where active learning can reduce the cost of labeling text data. We perform these simulations on three corpora that vary in size, document length, and domain. We find that in cases where the document class of interest is not balanced, researchers can label a fraction of the documents one would need using random sampling (or “passive” learning) to achieve equally performing classifiers. We further investigate how varying levels of intercoder reliability affect the active learning procedures and find that even with low reliability, active learning performs more efficiently than does random sampling.