Semiparametric estimation of treatment effect in a pretest-posttest study.


Journal Article

Inference on treatment effects in a pretest-posttest study is a routine objective in medicine, public health, and other fields. A number of approaches have been advocated. We take a semiparametric perspective, making no assumptions about the distributions of baseline and posttest responses. By representing the situation in terms of counterfactual random variables, we exploit recent developments in the literature on missing data and causal inference, to derive the class of all consistent treatment effect estimators, identify the most efficient such estimator, and outline strategies for implementation of estimators that may improve on popular methods. We demonstrate the methods and their properties via simulation and by application to a data set from an HIV clinical trial.

Full Text

Duke Authors

Cited Authors

  • Leon, S; Tsiatis, AA; Davidian, M

Published Date

  • December 2003

Published In

Volume / Issue

  • 59 / 4

Start / End Page

  • 1046 - 1055

PubMed ID

  • 14969484

Pubmed Central ID

  • 14969484

International Standard Serial Number (ISSN)

  • 0006-341X

Digital Object Identifier (DOI)

  • 10.1111/j.0006-341x.2003.00120.x


  • eng

Conference Location

  • United States