(Empirical) Bayes Approaches to Parallel Trends

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kwon, Soonwoo, Roth, Jonathan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909173812297728
author Kwon, Soonwoo
Roth, Jonathan
author_facet Kwon, Soonwoo
Roth, Jonathan
contents We consider Bayes and Empirical Bayes (EB) approaches for dealing with violations of parallel trends. In the Bayes approach, the researcher specifies a prior over both the pre-treatment violations of parallel trends $δ_{pre}$ and the post-treatment violations $δ_{post}$. The researcher then updates their posterior about the post-treatment bias $δ_{post}$ given an estimate of the pre-trends $δ_{pre}$. This allows them to form posterior means and credible sets for the treatment effect of interest, $τ_{post}$. In the EB approach, the prior on the violations of parallel trends is learned from the pre-treatment observations. We illustrate these approaches in two empirical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2404_11839
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle (Empirical) Bayes Approaches to Parallel Trends
Kwon, Soonwoo
Roth, Jonathan
Econometrics
Methodology
We consider Bayes and Empirical Bayes (EB) approaches for dealing with violations of parallel trends. In the Bayes approach, the researcher specifies a prior over both the pre-treatment violations of parallel trends $δ_{pre}$ and the post-treatment violations $δ_{post}$. The researcher then updates their posterior about the post-treatment bias $δ_{post}$ given an estimate of the pre-trends $δ_{pre}$. This allows them to form posterior means and credible sets for the treatment effect of interest, $τ_{post}$. In the EB approach, the prior on the violations of parallel trends is learned from the pre-treatment observations. We illustrate these approaches in two empirical applications.
title (Empirical) Bayes Approaches to Parallel Trends
topic Econometrics
Methodology
url https://arxiv.org/abs/2404.11839