Estimating treatment effects of longitudinal designs using regression models on propensity scores

Aristide C. Achy-Brou, Constantine E. Frangakis, Michael Griswold

Research output: Contribution to journalArticlepeer-review


We derive regression estimators that can compare longitudinal treatments using only the longitudinal propensity scores as regressors. These estimators, which assume knowledge of the variables used in the treatment assignment, are important for reducing the large dimension of covariates for two reasons. First, if the regression models on the longitudinal propensity scores are correct, then our estimators share advantages of correctly specified model-based estimators, a benefit not shared by estimators based on weights alone. Second, if the models are incorrect, the misspecification can be more easily limited through model checking than with models based on the full covariates. Thus, our estimators can also be better when used in place of the regression on the full covariates. We use our methods to compare longitudinal treatments for type II diabetes mellitus.

Original languageEnglish (US)
Pages (from-to)824-833
Number of pages10
Issue number3
StatePublished - Sep 2010


  • Admissibility
  • Longitudinal treatments
  • Observation study
  • Propensity scores

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Agricultural and Biological Sciences(all)
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Estimating treatment effects of longitudinal designs using regression models on propensity scores'. Together they form a unique fingerprint.

Cite this