Saved in:
Bibliographic Details
Main Author: Boussim, Onil
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.10946
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908637348233216
author Boussim, Onil
author_facet Boussim, Onil
contents This paper provides a nonparametric framework for causal inference with categorical outcomes under binary treatment and binary instrument settings. I decompose the observed joint probability of outcomes and treatment into marginal probabilities of potential outcomes and treatment, and association parameters that capture selection bias due to unobserved heterogeneity. Under a novel identifying assumption \emph{association similarity}, which requires the dependence between unobserved factors driving treatment and potential outcomes to be invariant across treatment states, I achieve point identification of the full distribution of potential outcomes. Recognizing that this assumption may be strong in some contexts, I propose two weaker alternatives: monotonic association, which restricts the direction of selection heterogeneity, and bounded association, which constrains its magnitude. These relaxed assumptions deliver sharp partial identification bounds that nest point identification as a special case and facilitate transparent sensitivity analysis. I illustrate the framework in an empirical application, estimating the causal effect of private health insurance on health outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10946
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Identifying treatment effects on categorical outcomes in IV models
Boussim, Onil
Econometrics
This paper provides a nonparametric framework for causal inference with categorical outcomes under binary treatment and binary instrument settings. I decompose the observed joint probability of outcomes and treatment into marginal probabilities of potential outcomes and treatment, and association parameters that capture selection bias due to unobserved heterogeneity. Under a novel identifying assumption \emph{association similarity}, which requires the dependence between unobserved factors driving treatment and potential outcomes to be invariant across treatment states, I achieve point identification of the full distribution of potential outcomes. Recognizing that this assumption may be strong in some contexts, I propose two weaker alternatives: monotonic association, which restricts the direction of selection heterogeneity, and bounded association, which constrains its magnitude. These relaxed assumptions deliver sharp partial identification bounds that nest point identification as a special case and facilitate transparent sensitivity analysis. I illustrate the framework in an empirical application, estimating the causal effect of private health insurance on health outcomes.
title Identifying treatment effects on categorical outcomes in IV models
topic Econometrics
url https://arxiv.org/abs/2510.10946