Research report

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

    01.06.2018

27

English This paper proposes 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. Our approach 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. Our effect estimators are shown to be asymptotically normal when the GPS is estimated by either a parametric or a nonparametric kernel-based method. We also provide a simulation study and an application to the Job Corps program.
Collections
Faculty
Faculté des sciences économiques et sociales
Language
  • English
Classification
Economics
Other electronic version

Faculté SES

Series statement
  • Working papers SES ; 495
License
License undefined
Identifiers
  • RERO DOC 309416
  • RERO R008804523
Persistent URL
https://folia.unifr.ch/unifr/documents/306658
Statistics

Document views: 25 File downloads:
  • WP_SES_495.pdf: 2