Situating Politics: Spatial Heterogeneity and the Study of Political History

Abstract While quantitative methods are routinely used to examine historical materials, critics take issue with the use of global regression models that attach a single parameter each predictor, thereby ignoring effects time and space, which together define context in events unfold. This problem can be addressed by allowing for heterogeneity, as highlighted proliferation work on time-varying models. In this article, I show how approach extended case spatial data using spatially varying coefficient models, an eye toward study electoral politics, where is especially common settings. Toward end, revisit critical field history: rise Populism American West period between 1890 1896. Upending popular narratives about correlates third-party support late nineteenth century, association vote share traditional predictors such economic hardship ethnic composition varied considerably from one place next, giving distinct varieties Populism—a finding missed mistake mathematically particular historically general. These findings have important theoretical empirical implications political action world heterogeneity increasingly recognized standard feature modern social science.