Endogenous Stratification in Randomized Experiments

© 2018 by the President and Fellows of Harvard College and the Massachusetts Institute of Technology. Policymakers are often interested in estimating how policy interventions affect the outcomes of those most in need of help. This concern has motivated the practice of disaggregating experimental res...

Full description

Bibliographic Details
Main Authors: Abadie, Alberto, Chingos, Matthew M, West, Martin R
Other Authors: Massachusetts Institute of Technology. Department of Economics
Format: Article
Language:English
Published: MIT Press - Journals 2021
Online Access:https://hdl.handle.net/1721.1/135812
_version_ 1811080349829038080
author Abadie, Alberto
Chingos, Matthew M
West, Martin R
author2 Massachusetts Institute of Technology. Department of Economics
author_facet Massachusetts Institute of Technology. Department of Economics
Abadie, Alberto
Chingos, Matthew M
West, Martin R
author_sort Abadie, Alberto
collection MIT
description © 2018 by the President and Fellows of Harvard College and the Massachusetts Institute of Technology. Policymakers are often interested in estimating how policy interventions affect the outcomes of those most in need of help. This concern has motivated the practice of disaggregating experimental results by groups constructed on the basis of an index of baseline characteristics that predicts the values of individual outcomes without the treatment. This paper shows that substantial biases may arise in practice if the index is estimated by regressing the outcome variable on baseline characteristics for the full sample of experimental controls. We propose alternative methods that correct this bias and show that they behave well in realistic scenarios.
first_indexed 2024-09-23T11:29:56Z
format Article
id mit-1721.1/135812
institution Massachusetts Institute of Technology
language English
last_indexed 2024-09-23T11:29:56Z
publishDate 2021
publisher MIT Press - Journals
record_format dspace
spelling mit-1721.1/1358122023-03-01T15:15:03Z Endogenous Stratification in Randomized Experiments Abadie, Alberto Chingos, Matthew M West, Martin R Massachusetts Institute of Technology. Department of Economics © 2018 by the President and Fellows of Harvard College and the Massachusetts Institute of Technology. Policymakers are often interested in estimating how policy interventions affect the outcomes of those most in need of help. This concern has motivated the practice of disaggregating experimental results by groups constructed on the basis of an index of baseline characteristics that predicts the values of individual outcomes without the treatment. This paper shows that substantial biases may arise in practice if the index is estimated by regressing the outcome variable on baseline characteristics for the full sample of experimental controls. We propose alternative methods that correct this bias and show that they behave well in realistic scenarios. 2021-10-27T20:29:26Z 2021-10-27T20:29:26Z 2018 2019-10-18T13:15:55Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/135812 en 10.1162/REST_A_00732 The Review of Economics and Statistics Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf MIT Press - Journals MIT Press
spellingShingle Abadie, Alberto
Chingos, Matthew M
West, Martin R
Endogenous Stratification in Randomized Experiments
title Endogenous Stratification in Randomized Experiments
title_full Endogenous Stratification in Randomized Experiments
title_fullStr Endogenous Stratification in Randomized Experiments
title_full_unstemmed Endogenous Stratification in Randomized Experiments
title_short Endogenous Stratification in Randomized Experiments
title_sort endogenous stratification in randomized experiments
url https://hdl.handle.net/1721.1/135812
work_keys_str_mv AT abadiealberto endogenousstratificationinrandomizedexperiments
AT chingosmatthewm endogenousstratificationinrandomizedexperiments
AT westmartinr endogenousstratificationinrandomizedexperiments