Extreme Quantile Treatment Effects under Endogeneity: Evaluating Policy Effects for the Most Vulnerable Individuals

TL;DR

This paper presents a new method for estimating extreme quantile treatment effects under endogeneity, applicable to various empirical designs, ensuring robustness in sparse tail data, and revealing negative effects for the most disadvantaged individuals.

Contribution

It introduces a novel approach combining regular variation and subsampling for robust inference of extreme QTEs under endogeneity across multiple research designs.

Findings

Negative QTEs for the lowest quantiles in job training impact.

Method performs robustly in sparse tail data scenarios.

Contrasts with previous positive QTE findings for intermediate quantiles.

Abstract

We introduce a novel method for estimating and conducting inference about extreme quantile treatment effects (QTEs) in the presence of endogeneity. Our approach is applicable to a broad range of empirical research designs, including instrumental variables design and regression discontinuity design, among others. By leveraging regular variation and subsampling, the method ensures robust performance even in extreme tails, where data may be sparse or entirely absent. Simulation studies confirm the theoretical robustness of our approach. Applying our method to assess the impact of job training provided by the Job Training Partnership Act (JTPA), we find significantly negative QTEs for the lowest quantiles (i.e., the most disadvantaged individuals), contrasting with previous literature that emphasizes positive QTEs for intermediate quantiles.