Concerns over free riding in NATO are widespread. An intuitive approach to analyzing free riding is treating it as a systematic pattern of spatial interdependence between the allies: how does a NATO member's defense spending react to changes in other allies' military expenditures? While recent work has found statistically significant free riding (negative spatial interdependence in the outcomes), it suffers from important limitations. First, this research does not adequately account for temporal dependence. Second, it does not quantify the effect of interest. Accounting directly for temporal dependence provides a meaningfully distinct perspective on the within-alliance dynamics, demonstrating that the spatiotemporal effect of free riding is, in fact, more substantial than its short-run effect, challenging inferences of static spatial models. We discuss the relevant practical and theoretical implications.

This paper proposes a Bayesian multilevel spatio-temporal model with a time-varying spatial autoregressive coefficient to estimate temporally heterogeneous network interdependence. To tackle the classic reflection problem, we use multiple factors to control for confounding caused by latent homophily and common exposures. We develop a Markov Chain Monte Carlo algorithm to estimate parameters and adopt Bayesian shrinkage to determine the number of factors. Tests on simulated and empirical data show that the proposed model improves identification of network interdependence and is robust to misspecification. Our method is applicable to various types of networks and provides a simpler and more flexible alternative to coevolution models.

Political actors often interact spatially, and move around. However, with a few exceptions, existing political research has analyzed spatial dependence among actors with fixed geographic locations. Focusing on fixated geographic units prevents us from probing dependencies in spatial interaction between spatially dynamic actors, which are common in some areas of political science, such as sub-national conflict studies. In this note, we propose a method to account for spatial dependence in dyadic interactions between moving actors. Our method uses the spatiotemporal histories of dyadic interactions to project locations of future interactions—projected actor locations (PALs). PALs can, in turn, be used to model the likelihood of future dyadic interactions. In a replication and extension of a recent study of subnational conflict, we find that using PALs improves the predictive performance of the model and indicates that there is a clear relationship between actors’ past conflict locations and the likelihood of future conflicts.

Previous research reports that parties in established European democracies learn from and emulate the successful election strategies of foreign incumbents, i.e., successful parties are influential abroad. We theorize that—in addition to incumbency (or success)—exchange takes place through transnational party alliances in the European Union. Relying on party manifesto data and spatial econometric analyses, we show that belonging to the same European Parliament (EP) party group enhances learning and emulation processes between national political parties. Estimated short- and long-term effects are approximately two and three times greater when foreign incumbents are in the same EP party group compared to other foreign incumbents. Our results have implications for our understanding of how transnational party groups influence national parties’ policy positions.

Across disciplines, scholars strive to better understand individuals’ milieus—the people, places, and institutions individuals encounter in their daily lives. In particular, political scientists argue that racial and ethnic context shapes attitudes about candidates, policies, and fellow citizens. Yet, the current standard of measuring milieus is to place survey respondents in a geographic container and then to ascribe all that container's characteristics to the individual's milieu. Using a new dataset of over 2.6 million GPS records from over 400 individuals, we compare conventional static measures of racial and ethnic context to dynamic, precise measures of milieus. We demonstrate how low-level static measures tend to overstate how extreme individuals’ racial and ethnic contexts are and offer suggestions for future researchers.

The use of spatial econometric models in political science has steadily risen in recent years. However, the interpretation of these models has generally ignored the important substantive, and even spatial, nature of the estimated effects. This leaves many papers with a (non-spatial) interpretation of coefficients on the covariates and a brief discussion of the sign and strength of the spatial parameter. We introduce a general approach to interpreting spatial models and provide several avenues for an exposition of substantive spatial effects. Our approach can be generalized to most models in the spatial econometric taxonomy. Building on the example of the diffusion of democracy, we elucidate how our approach can be applied to modern political science problems.

Mixed-methods designs, especially those in which case selection is regression-based, have become popular across the social sciences. In this paper, we highlight why tools from spatial analysis—which have largely been overlooked in the mixed-methods literature—can be used for case selection and be particularly fruitful for theory development. We discuss two tools for integrating quantitative and qualitative analysis: (1) spatial autocorrelation in the outcome of interest; and (2) spatial autocorrelation in the residuals of a regression model. The case selection strategies presented here enable scholars to systematically use geography to learn more about their data and select cases that help identify scope conditions, evaluate the appropriate unit or level of analysis, examine causal mechanisms, and uncover previously omitted variables.