Identification of multi-valued treatment effects with unobserved heterogeneity

TL;DR

This paper develops conditions for identifying treatment effects in complex settings with unobserved heterogeneity, using monotonicity assumptions and providing explicit formulas for local effects.

Contribution

It introduces new identification conditions for multi-valued treatments with unobserved heterogeneity, including closed-form expressions for local treatment effects.

Findings

Established sufficient conditions for treatment effect identification.

Derived closed-form expressions for local treatment effects.

Illustrated the usefulness with practical examples.

Abstract

In this paper, we establish sufficient conditions for identifying treatment effects on continuous outcomes in endogenous and multi-valued discrete treatment settings with unobserved heterogeneity. We employ the monotonicity assumption for multi-valued discrete treatments and instruments, and our identification condition has a clear economic interpretation. In addition, we identify the local treatment effects in multi-valued treatment settings and derive closed-form expressions of the identified treatment effects. We provide examples to illustrate the usefulness of our result.