Complex models are of increasing interest to social scientists. Researchers interested in prediction generally favor flexible, robust approaches, while those interested in causation are often interested in modeling nuanced treatment structures and confounding relationships. Unfortunately, estimators of complex models often scale poorly, especially if they seek to maintain interpretability. In this paper, we present an example of such a conundrum and show how optimization can alleviate the worst of these concerns. Specifically, we introduce bigKRLS, which offers a variety of statistical and computational improvements to the Hainmueller and Hazlett (2013) Kernel-Regularized Least Squares (KRLS) approach. As part of our improvements, we decrease the estimator’s single-core runtime by 50% and reduce the estimator’s peak memory usage by an order of magnitude. We also improve uncertainty estimates for the model’s average marginal effect estimates—which we test both in simulation and in practice—and introduce new visual and statistical tools designed to assist with inference under the model. We further demonstrate the value of our improvements through an analysis of the 2016 presidential election, an analysis that would have been impractical or even infeasible for many users with existing software.

Does attentiveness matter in survey responses? Do more attentive survey participants give higher quality responses? Using data from a recent online survey that identified inattentive respondents using instructed-response items, we demonstrate that ignoring attentiveness provides a biased portrait of the distribution of critical political attitudes and behavior. We show that this bias occurs in the context of both typical closed-ended questions and in list experiments. Inattentive respondents are common and are more prevalent among the young and less educated. Those who do not pass the trap questions interact with the survey instrument in distinctive ways: they take less time to respond; are more likely to report nonattitudes; and display lower consistency in their reported choices. Inattentiveness does not occur completely at random and failing to properly account for it may lead to inaccurate estimates of the prevalence of key political attitudes and behaviors, of both sensitive and more prosaic nature.

Multiplicative interaction models are widely used in social science to examine whether the relationship between an outcome and an independent variable changes with a moderating variable. Current empirical practice tends to overlook two important problems. First, these models assume a linear interaction effect that changes at a constant rate with the moderator. Second, estimates of the conditional effects of the independent variable can be misleading if there is a lack of common support of the moderator. Replicating 46 interaction effects from 22 recent publications in five top political science journals, we find that these core assumptions often fail in practice, suggesting that a large portion of findings across all political science subfields based on interaction models are fragile and model dependent. We propose a checklist of simple diagnostics to assess the validity of these assumptions and offer flexible estimation strategies that allow for nonlinear interaction effects and safeguard against excessive extrapolation. These statistical routines are available in both R and STATA.

Surveys are a key tool for understanding political behavior, but they are subject to biases that render their estimates about the frequency of socially desirable behaviors inaccurate. For decades the American National Election Study (ANES) has overestimated voter turnout, though the causes of this persistent bias are poorly understood. The face-to-face component of the 2012 ANES produced a turnout estimate at least 13 points higher than the benchmark voting-eligible population turnout rate. We consider three explanations for this overestimate in the survey: nonresponse bias, over-reporting and the possibility that the ANES constitutes an inadvertent mobilization treatment. Analysis of turnout data supplied by voter file vendors allows the three phenomena to be measured for the first time in a single survey. We find that over-reporting is the largest contributor, responsible for six percentage points of the turnout overestimate, while nonresponse bias and mobilization account for an additional 4 and 3 percentage points, respectively.

We introduce a Bayesian approach to conduct inferential analyses on dyadic data while accounting for interdependencies between observations through a set of additive and multiplicative effects (AME). The AME model is built on a generalized linear modeling framework and is thus flexible enough to be applied to a variety of contexts. We contrast the AME model to two prominent approaches in the literature: the latent space model (LSM) and the exponential random graph model (ERGM). Relative to these approaches, we show that the AME approach is (a) to be easy to implement; (b) interpretable in a general linear model framework; (c) computationally straightforward; (d) not prone to degeneracy; (e) captures first-, second-, and third-order network dependencies; and (f) notably outperforms ERGMs and LSMs on a variety of metrics and in an out-of-sample context. In summary, AME offers a straightforward way to undertake nuanced, principled inferential network analysis for a wide range of social science questions.

There is an ongoing debate about whether human rights standards have changed over the last 30 years. The evidence for or against this shift relies upon indicators created by human coders reading the texts of human rights reports. To help resolve this debate, we suggest translating the question of changing standards into a supervised learning problem. From this perspective, the application of consistent standards over time implies a time-constant mapping from the textual features in reports to the human coded scores. Alternatively, if the meaning of abuses have evolved over time, then the same textual features will be labeled with different numerical scores at distinct times. Of course, while the mapping from natural language to numerical human rights score is a highly complicated function, we show that these two distinct data generation processes imply divergent overall patterns of accuracy when we train a wide variety of algorithms on older versus newer sets of observations to learn how to automatically label texts with scores. Our results are consistent with the expectation that standards of human rights have changed over time.

Many bilateral relationships requiring mutual agreement produce observable networks that are symmetric (undirected). However, the unobserved, asymmetric (directed) network is frequently the object of scientific interest. We propose a method that probabilistically reconstructs the latent, asymmetric network from the observed, symmetric graph in a regression-based framework. We apply this model to the bilateral investment treaty network. Our approach successfully recovers the true data generating process in simulation studies, extracts new, politically relevant information about the network structure inaccessible to alternative approaches, and has superior predictive performance.

Do judges telegraph their preferences during oral arguments? Using the U.S. Supreme Court as our example, we demonstrate that Justices implicitly reveal their leanings during oral arguments, even before arguments and deliberations have concluded. Specifically, we extract the emotional content of over 3,000 hours of audio recordings spanning 30 years of oral arguments before the Court. We then use the level of emotional arousal, as measured by vocal pitch, in each of the Justices’ voices during these arguments to accurately predict many of their eventual votes on these cases. Our approach yields predictions that are statistically and practically significant and robust to including a range of controls; in turn, this suggests that subconscious vocal inflections carry information that legal, political, and textual information do not.

Does exposure to the refugee crisis fuel support for extreme-right parties? Despite heated debates about the political repercussions of the refugee crisis in Europe, there exists very little—and sometimes conflicting—evidence with which to assess the impact of a large influx of refugees on natives’ political attitudes and behavior. We provide causal evidence from a natural experiment in Greece, where some Aegean islands close to the Turkish border experienced sudden and drastic increases in the number of Syrian refugees while other islands slightly farther away—but with otherwise similar institutional and socioeconomic characteristics—did not. Placebo tests suggest that precrisis trends in vote shares for exposed and nonexposed islands were virtually identical. This allows us to obtain unbiased estimates of the electoral consequences of the refugee crisis. Our study shows that among islands that faced a massive but transient inflow of refugees passing through just before the September 2015 election, vote shares for Golden Dawn, the most extreme-right party in Europe, moderately increased by 2 percentage points (a 44 percent increase at the average). The finding that mere exposure to the refugee crisis is sufficient to fuel support for extreme-right parties has important implications for our theoretical understanding of the drivers of antirefugee backlash.

We offer a dynamic Bayesian forecasting model for multiparty elections. It combines data from published pre-election public opinion polls with information from fundamentals-based forecasting models. The model takes care of the multiparty nature of the setting and allows making statements about the probability of other quantities of interest, such as the probability of a plurality of votes for a party or the majority for certain coalitions in parliament. We present results from two ex ante forecasts of elections that took place in 2017 and are able to show that the model outperforms fundamentals-based forecasting models in terms of accuracy and the calibration of uncertainty. Provided that historical and current polling data are available, the model can be applied to any multiparty setting.