1 option
Program evaluation of treatment effect heterogeneity theory and applications Chiyoung Ahn
- Format:
- Book
- Thesis/Dissertation
- Author/Creator:
- Ahn, Chiyoung, author.
- Language:
- English
- Subjects (All):
- Statistics.
- Law.
- Public policy.
- 0501.
- 0511.
- 0398.
- 0630.
- 0463.
- Local Subjects:
- Statistics.
- Law.
- Public policy.
- 0501.
- 0511.
- 0398.
- 0630.
- 0463.
- Genre:
- Academic theses
- Physical Description:
- 1 online resource (216 pages)
- Contained In:
- Dissertations Abstracts International 87-12B
- Place of Publication:
- Ann Arbor : ProQuest Dissertations and Theses, 2026
- Language Note:
- English
- Summary:
- This dissertation develops identification and inference methods for treatment effect heterogeneity, with applications to program evaluation. The first chapter develops a framework that identifies and tests treatment effect heterogeneity using prognostic variables-risk scores or proxy means that predict untreated outcomes without directly influencing treatment effects; I formalize the identifying assumptions, establish identification of a treatment response kernel that summarizes how treated outcomes are generated from untreated outcomes, propose a plug-in estimator, derive its asymptotic distribution, and develop a test for structural hypotheses such as monotonicity. The second chapter introduces a distributional regression framework that identifies the distribution of treatment effects by leveraging prognostic variables, develops a two-step estimator with large-sample theory, and applies the method to the National Job Training Partnership Act (JTPA) Study with remote past earnings as prognostic variables, uncovering substantial previously undocumented offsetting heterogeneity: a sizable subset of participants gain more than $10,000 cumulatively over the 30-month follow-up despite modest mean effects. The third chapter (co-authored with Hiroyuki Kasahara) develops event-study designs for discrete outcomes under transition independence-transition dynamics conditional on past outcomes that are identical for treated and control units-showing how this assumption identifies dynamic treatment effects on binary and ordered outcomes, and provides estimators and inference procedures.
- Notes:
- Source: Dissertations Abstracts International, Volume: 87-12, Section: B.
- Advisors: Todd, Petra Committee members: Adusumilli, Karun; Cheng, Xu; Kasahara, Hiroyuki
- Ph.D. University of Pennsylvania 2026
- Vendor supplied data
- Local Notes:
- School code: 0175
- ISBN:
- 9798247983101
- Access Restriction:
- Restricted for use by site license
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.