Direct and indirect effects of continuous treatments based on generalized propensity score weighting

publication
article
mediation analysis
continuous treatment
weighting
generalized propensity score
UniFr
R
Authors
Affiliations

Yu-Chin Hsu

Academia Sinica, Institute of Economics; Department of Finance, National Central

Martin Huber

University of Fribourg, Dept. of Economics

Ying-Ying Lee

University of California Irvine, Dept. of Economics

Layal Lettry

Swiss Federal Agency for Social Insurances, Mathematics Group

Published

April 14, 2020

How to disentangle the total causal effect of a continuous treatment on an outcome into natural direct and indirect effects using the generalized propensity score?

Abstract

Huber et al. (2020) propose in this article semi- and nonparametric methods for disentangling the total causal effect of a continuous treatment on an outcome variable into its natural direct effect and the indirect effect that operates through one or several intermediate variables or mediators.

Huber et al. (2020) have an approach which is based on weighting observations by the inverse of two versions of the generalized propensity score (GPS), namely the conditional density of treatment either given observed covariates or given covariates and the mediator.

Huber et al. (2020) show that the effect estimators are asymptotically normal when the GPS is estimated by either a parametric or a nonparametric kernel-based method. A simulation study and an application to the Job Corps program is also provided.

References

Huber, Martin, Yu-Chin Hsu, Ying-Ying Lee, and Layal Lettry. 2020. “Direct and Indirect Effects of Continuous Treatments Based on Generalized Propensity Score Weighting.” Journal of Applied Econometrics 35 (7): 814–40. https://doi.org/https://doi.org/10.1002/jae.2765.

Citation

BibTeX citation:
@online{hsu2020,
  author = {Hsu, Yu-Chin and Huber, Martin and Lee, Ying-Ying and
    Lettry, Layal},
  title = {Direct and Indirect Effects of Continuous Treatments Based on
    Generalized Propensity Score Weighting},
  date = {2020-04-14},
  url = {https://doi.org/10.1002/jae.2765},
  langid = {en}
}
For attribution, please cite this work as:
Hsu, Yu-Chin, Martin Huber, Ying-Ying Lee, and Layal Lettry. 2020. “Direct and Indirect Effects of Continuous Treatments Based on Generalized Propensity Score Weighting.” April 14, 2020. https://doi.org/10.1002/jae.2765.