STADL Up! The Spatiotemporal Autoregressive Distributed Lag Model for TSCS Data Analysis

Time-series cross-section (TSCS) data are prevalent in political science, yet many distinct challenges presented by TSCS remain underaddressed. We focus on how dependence both space and time complicates estimating either spatial or temporal dependence, dynamics, effects. Little is known about modeling one of cross-sectional well while neglecting the other affects results analysis. demonstrate analytically through simulations misspecification inflates estimates dimension’s thereby induces biased tests covariate Therefore, we recommend spatiotemporal autoregressive distributed lag (STADL) model with lags as an effective general starting point for specification. illustrate two example reanalyses provide R code to facilitate researchers’ implementation—from automation common spatial-weights matrices ( W ) estimated effects/response calculations—for their own analyses.