Propensity Score Matching for Multiple Treatments using Generalized Boosted Models

12 Pages Posted: 9 Apr 2021

See all articles by Yuchen Gao

Yuchen Gao

Tsinghua University - School of Public Policy and Management

Yimei Hu

Aalborg University - Department of Business and Management

Xielin Liu

Chinese Academy of Sciences (CAS) - School of Economics and Management

Huanren Zhang

University of Southern Denmark - Department of Economics

Date Written: March 31, 2021

Abstract

Propensity score analysis becomes complicated when there are multiple treatments. Existing studies bypass this complication by focusing on two of the treatments at a time and calculate the pairwise treatment effects, but this pairwise comparison does not allow advanced analysis that investigates how different treatments interact with other variables to influence the dependent variable. In this paper, we show how to obtain a matched sample with balanced pretreatment variables for a dataset with multiple treatments. Using Generalized Boosted Models (GBMs) to calculate the generalized propensity score vector, our proposed procedure match observations on a multi-dimensional space. Researchers to directly conduct complex econometric analysis on the matched sample using standard statistical packages without the necessity of additional programming. Our results also demonstrate the advantage of GBMs over the commonly used multinomial logistic regressions in calculating the generalized propensity score.

Keywords: propensity score matching, multiple treatments, generalized boosted model, generalized propensity score

JEL Classification: O32, O38, H25

Suggested Citation

Gao, Yuchen and Hu, Yimei and Liu, Xielin and Zhang, Huanren, Propensity Score Matching for Multiple Treatments using Generalized Boosted Models (March 31, 2021). Available at SSRN: https://ssrn.com/abstract=3821608

Yuchen Gao

Tsinghua University - School of Public Policy and Management ( email )

Beijing, 100084
China

Yimei Hu

Aalborg University - Department of Business and Management ( email )

Aalborg, DK-9220
Denmark

Xielin Liu

Chinese Academy of Sciences (CAS) - School of Economics and Management ( email )

No.80, Zhongguancun East Road, Haidian District
Beijing
China

Huanren Zhang (Contact Author)

University of Southern Denmark - Department of Economics ( email )

Odense
Denmark

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
579
Abstract Views
1,536
Rank
87,546
PlumX Metrics