Research

Many events and policies (treatments) occur at specific spatial locations, with researchers interested in their effects on nearby units of interest. I approach the spatial treatment setting from an experimental perspective: What ideal experiment would we design to estimate the causal effects of spatial treatments? This perspective motivates a comparison between individuals near realized treatment locations and individuals near counterfactual (unrealized) candidate locations, which differs from current empirical practice. I derive design-based standard errors that are straightforward to compute irrespective of spatial correlations in outcomes. Furthermore, I propose machine learning methods to find counterfactual candidate locations using observational data under unconfounded assignment of the treatment to locations. I apply the proposed methods to study the causal effects of grocery stores on foot traffic to nearby businesses during COVID-19 shelter-in-place policies, finding a substantial positive effect at a very short distance, with no effect at larger distances.

This paper develops a method that learns the relationship between hypothetical responses and real choices in observational data, and then uses that estimated relationship to predict the effect of counterfactuals. After developing the econometric theory for the estimator, we demonstrate that it can be applied in settings where standard methods are not applicable. In both a lab and field setting we show it can recover accurate estimates of treatment effects that are close to ground truth experimental estimates.

We develop new semiparametric methods for estimating treatment effects. We focus on settings where the outcome distributions may be thick tailed, where treatment effects may be small, where sample sizes are large and where assignment is completely random. This setting is of particular interest in recent online experimentation. We propose using parametric models for the treatment effects, leading to semiparametric models for the outcome distributions. We derive the semiparametric efficiency bound for the treatment effects for this setting, and propose efficient estimators. In the leading case with constant quantile treatment effects one of the proposed efficient estimators has an interesting interpretation as a weighted average of quantile treatment effects, with the weights proportional to minus the second derivative of the log of the density of the potential outcomes. Our analysis also suggests an extension of Huber's model and trimmed mean to include asymmetry.

Health insurance systems in many countries reimburse hospitals through fixed prices based on the diagnosis-related groups (DRGs) of patients. We quantify the effects of price and income changes for the full spectrum of hospital services as average and heterogeneous elasticities of quantities (number of admissions) and quality-related outcomes. For our empirical analysis, we use data on over 160 million hospital admissions, constituting the universe of hospital admissions in Germany between 2005 and 2016. Our identification strategy is based on instruments exploiting a two-year lag in regulatory price setting. The strategy lends itself to a placebo test demonstrating that our instruments do not have substantive anticipatory direct effects. We find that the compensated own-price elasticity of quantity is positive (0.2), while the income elasticity is negative (-0.15). On net, increasing all prices increases costs due to a behavioral response of larger quantities in addition to the mechanical increase.