Search for: All records

Abstract To comprehensively evaluate a public policy intervention, researchers must consider the effects of the policy not just on the implementing region, but also nearby, indirectly affected regions. For example, an excise tax on sweetened beverages in Philadelphia, Pennsylvania was shown to not only be associated with a decrease in volume sales of taxed beverages in Philadelphia, but also an increase in sales in nontaxed bordering counties. The latter association may be explained by cross-border shopping behaviours of Philadelphia residents and indicate a causal effect of the tax on nearby regions, which may drastically offset the total effect of the intervention. In this paper, we adapt doubly robust difference-in-differences methodology to estimate distinct causal effects on the implementing and neighbouring control regions when they are geographically separable and data exists from an unaffected control region. Our approach adjusts for potential confounding in quasi-experimental evaluations and relaxes standard assumptions on model specification while accounting for geographically separable interference, repeated observations, spatial correlation, and unknown effect heterogeneity. We apply these methods to evaluate the effect of the Philadelphia beverage tax on taxed beverage sales in 231 Philadelphia and bordering county stores. We also use our methods to explore effect heterogeneity across geographical features.