Extreme Continuous Treatment Effects: Measures, Estimation and Inference

TL;DR

This paper develops methods for estimating and inferring treatment effects in the extreme tails of the potential outcome distribution for continuous treatments, using extreme value theory to handle rare but impactful events.

Contribution

It introduces the extreme quantile treatment effect (EQTE) and extreme average treatment effect (EATE), providing a unified framework for tail analysis with uniform inference.

Findings

Method performs well in finite sample simulations

Empirical application demonstrates practical utility

Theoretical results support uniform inference for tail effects

Abstract

This paper concerns estimation and inference for treatment effects in deep tails of the counterfactual distribution of unobservable potential outcomes corresponding to a continuously valued treatment. We consider two measures for the deep tail characteristics: the extreme quantile function and the tail mean function defined as the conditional mean beyond a quantile level. Then we define the extreme quantile treatment effect (EQTE) and the extreme average treatment effect (EATE), which can be identified through the commonly adopted unconfoundedness condition and estimated with the aid of extreme value theory. Our limiting theory is for the EQTE and EATE processes indexed by a set of quantile levels and hence facilitates uniform inference. Simulations suggest that our method works well in finite samples and an empirical application illustrates its practical merit.