Political scientists are increasingly interested in the geographic distribution of political and economic phenomena. Unlike distribution measures at the individual level, geographic distributions depend on the “unit question” in which researchers choose the appropriate political subdivision to analyze, such as nations, subnational regions, urban and rural areas, or electoral districts. We identify concerns with measuring geographic distribution and comparing distributions within and across political units. In particular, we highlight the potential for threats to inference based on the modifiable areal unit problem (MAUP), whereby measuring concepts at different unit aggregations alters the observed value. We offer tangible options for researchers to improve their research design and data analysis to limit the MAUP. To help manage the measurement error when the unit of observation is unclear or appropriate data are not available, we introduce a new measure of geographic distribution that accounts for fluctuations in the scale and number of political units considered. We demonstrate using Monte Carlo simulations that our measure is more reliable and stable across political units than commonly used indicators because it reduces measurement fluctuations associated with the MAUP.

Pesaran, Shin, and Smith (2001) (PSS) proposed a bounds procedure for testing for the existence of long run cointegrating relationships between a unit root dependent variable ($y_{t}$) and a set of weakly exogenous regressors $\boldsymbol{x}_{t}$ when the analyst does not know whether the independent variables are stationary, unit root, or mutually cointegrated processes. This procedure recognizes the analyst’s uncertainty over the nature of the regressors but not the dependent variable. When the analyst is uncertain whether $y_{t}$ is a stationary or unit root process, the test statistics proposed by PSS are uninformative for inference on the existence of a long run relationship (LRR) between $y_{t}$ and $\boldsymbol{x}_{t}$. We propose the long run multiplier (LRM) test statistic as a means of testing for LRRs without knowing whether the series are stationary or unit roots. Using stochastic simulations, we demonstrate the behavior of the test statistic given uncertainty about the univariate dynamics of both $y_{t}$ and $\boldsymbol{x}_{t}$, illustrate the bounds of the test statistic, and generate small sample and approximate asymptotic critical values for the upper and lower bounds for a range of sample sizes and model specifications. We demonstrate the utility of the bounds framework for testing for LRRs in models of public policy mood and presidential success.

According to spatial models of political competition, parties strategically adjust their ideological positions to movements made by rival parties. Spatial econometric techniques have been proposed to empirically model such interdependencies and to closely convert theoretical expectations into statistical models. Yet, these models often ignore that the parties’ ideological positions are latent variables and, as such, accompanied by a quantifiable amount of uncertainty. As a result, the implausible assumption of perfectly measured covariates impedes a proper evaluation of theoretical propositions. In order to bridge this gap between theory and empirics, the present work combines a spatial econometric model and a Bayesian dynamic item response model. The proposed model accurately accounts for measurement uncertainty and simultaneously estimates the parties’ ideological positions and their spatial interdependencies. To verify the model’s utility, I apply it to recorded votes from the sixteen German state legislatures in the period from 1988 to 2016. While exhibiting a notable degree of ideological mobility, the results indicate only moderate spatial dependencies among parties of the same party family. More importantly, the analysis illustrates how measurement uncertainty can lead to substantively different results which stresses the importance of appropriately incorporating theoretical expectations into statistical models.

This paper introduces an instrumental variables framework for analyzing how external factors that affect survey response rates can also affect the composition of the sample of respondents. The method may be useful for studying survey representativeness, and for assessing the effectiveness of some of the conventional corrections for survey nonresponse bias.

The paper applies the method to data collected in the 2011 Swiss Electoral Study (SES), in which survey participation incentives were randomly assigned across members of the original survey sample. The empirical analysis shows that the incentives increased response rates substantially. Estimates of a new instrumental variable parameter called the Complier Average Survey Response (CASR) suggest that the incentives induced participation among people with more nationalist political opinions than those who would have participated without the incentives. Weighting the respondent data to match the covariate distribution in the target population did not account for the discrepancy in attitudes between the two groups, suggesting that the weights would not succeed in removing nonresponse bias.

The analysis of political texts from parliamentary speeches, party manifestos, social media, or press releases forms the basis of major and growing fields in political science, not least since advances in “text-as-data” methods have rendered the analysis of large text corpora straightforward. However, a lot of sources of political speech are not regularly transcribed, and their on-demand transcription by humans is prohibitively expensive for research purposes. This class includes political speech in certain legislatures, during political party conferences as well as television interviews and talk shows. We showcase how scholars can use automatic speech recognition systems to analyze such speech with quantitative text analysis models of the “bag-of-words” variety. To probe results for robustness to transcription error, we present an original “word error rate simulation” (WERSIM) procedure implemented in $R$. We demonstrate the potential of automatic speech recognition to address open questions in political science with two substantive applications and discuss its limitations and practical challenges.

Political scientists are increasingly interested in causal mediation, and to this end, recent studies focus on estimating a quantity called the controlled direct effect (CDE). The CDE measures the strength of the causal relationship between a treatment and outcome when a mediator is fixed at a given value. To estimate the CDE, Joffe and Greene (2009) and Vansteelandt (2009) developed the method of sequential g-estimation, which was introduced to political science by Acharya, Blackwell, and Sen (2016). In this letter, we propose an alternative method called “regression-with-residuals” (RWR) for estimating the CDE. In special cases, we show that these two methods are algebraically equivalent. Yet, unlike sequential g-estimation, RWR can easily accommodate several types of effect moderation, including cases in which the effect of the mediator on the outcome is moderated by a posttreatment confounder. Although common in the social sciences, this type of effect moderation is typically assumed away in applications of sequential g-estimation, which may lead to bias if effect moderation is in fact present. We illustrate RWR by estimating the CDE of negative media framing on public support for immigration, controlling for respondent anxiety.

Recent research has questioned the value of statistical learning methods for producing accurate predictions in the criminal justice context. Using results from respondents on Amazon Mechanical Turk (MTurkers) who were asked to predict recidivism, Dressel and Farid (2018) argue that nonexperts can achieve predictive accuracy and fairness on par with algorithmic approaches that employ statistical learning models. Analyzing the same data from the original study, this comment employs additional techniques and compares the quality of the predicted probabilities output from statistical learning procedures versus the MTurkers’ evaluations. The metrics presented indicate that statistical approaches do, in fact, outperform the nonexperts in important ways. Based on these new analyses, it is difficult to accept the conclusion presented in Dressel and Farid (2018) that their results “cast significant doubt on the entire effort of algorithmic recidivism prediction.”

Though used frequently in machine learning, boosted decision trees are largely unused in political science, despite many useful properties. We explain how to use one variant of boosted decision trees, AdaBoosted decision trees (ADTs), for social science predictions. We illustrate their use by examining a well-known political prediction problem, predicting U.S. Supreme Court rulings. We find that our ADT approach outperforms existing predictive models. We also provide two additional examples of the approach, one predicting the onset of civil wars and the other predicting county-level vote shares in U.S. presidential elections.

Social scientists are frequently interested in how populations evolve over time. Creating poststratification weights for surveys, for example, requires information on the weighting variables’ joint distribution in the target population. Typically, however, population data are sparsely available across time periods. Even when population data are observed, the content and structure of the data—which variables are observed and whether their marginal or joint distributions are known—differ across time, in ways that preclude straightforward interpolation. As a consequence, survey weights are often based only on the small subset of auxiliary variables whose joint population distribution is observed regularly over time, and thus fail to take full advantage of auxiliary information. To address this problem, we develop a dynamic Bayesian ecological inference model for estimating multivariate categorical distributions from sparse, irregular, and noisy data on their marginal (or partially joint) distributions. Our approach combines (1) a Dirichlet sampling model for the observed margins conditional on the unobserved cell proportions; (2) a set of equations encoding the logical relationships among different population quantities; and (3) a Dirichlet transition model for the period-specific proportions that pools information across time periods. We illustrate this method by estimating annual U.S. phone-ownership rates by race and region based on population data irregularly available between 1930 and 1960. This approach may be useful in a wide variety of contexts where scholars wish to make dynamic ecological inferences about interior cells from marginal data. A new R package estsubpop implements the method.