TY - JOUR
T1 - Estimation of Heterogeneous Individual Treatment Effects With Endogenous Treatments
AU - Feng, Qian
AU - Vuong, Quang
AU - Xu, Haiqing
N1 - Funding Information:
We thank the Editor, the Associate Editor, and a referee for their comments which have greatly improved the paper. We also thank Jason Abrevaya, Isaiah Andrews, Robert Leili, Leigh Linden, Matt Masten, Andres Santos as well as seminar participants at NYU, University of Texas at Austin, Bank of Italy, Texas Econometrics Camp 2015, and 2016 CEME conference at Duke University for their helpful comments.
Publisher Copyright:
© 2019, © 2019 American Statistical Association.
PY - 2020/1/2
Y1 - 2020/1/2
N2 - This article estimates individual treatment effects (ITE) and its probability distribution in a triangular model with binary-valued endogenous treatments. Our estimation procedure takes two steps. First, we estimate the counterfactual outcome and hence, the ITE for every observational unit in the sample. Second, we estimate the ITE density function of the whole population. Our estimation method does not suffer from the ill-posed inverse problem associated with inverting a nonlinear functional. Asymptotic properties of the proposed method are established. We study its finite sample properties in Monte Carlo experiments. We also illustrate our approach with an empirical application assessing the effects of 401(k) retirement programs on personal savings. Our results show that there exists a small but statistically significant proportion of individuals who experience negative effects, although the majority of ITEs is positive. Supplementary materials for this article are available online.
AB - This article estimates individual treatment effects (ITE) and its probability distribution in a triangular model with binary-valued endogenous treatments. Our estimation procedure takes two steps. First, we estimate the counterfactual outcome and hence, the ITE for every observational unit in the sample. Second, we estimate the ITE density function of the whole population. Our estimation method does not suffer from the ill-posed inverse problem associated with inverting a nonlinear functional. Asymptotic properties of the proposed method are established. We study its finite sample properties in Monte Carlo experiments. We also illustrate our approach with an empirical application assessing the effects of 401(k) retirement programs on personal savings. Our results show that there exists a small but statistically significant proportion of individuals who experience negative effects, although the majority of ITEs is positive. Supplementary materials for this article are available online.
KW - 401(k) retirement programs
KW - Binary endogenous variable
KW - Counterfactual mapping
KW - Individual treatment effects
KW - Nonseparable triangular models
UR - http://www.scopus.com/inward/record.url?scp=85064498906&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85064498906&partnerID=8YFLogxK
U2 - 10.1080/01621459.2018.1543121
DO - 10.1080/01621459.2018.1543121
M3 - Article
AN - SCOPUS:85064498906
SN - 0162-1459
VL - 115
SP - 231
EP - 240
JO - Journal of the American Statistical Association
JF - Journal of the American Statistical Association
IS - 529
ER -