Testing treatment effects in unconfounded studies under model misspecification: Logistic regression, discretization, and their combination

DSpace/Manakin Repository

Testing treatment effects in unconfounded studies under model misspecification: Logistic regression, discretization, and their combination

Citable link to this page

 

 
Title: Testing treatment effects in unconfounded studies under model misspecification: Logistic regression, discretization, and their combination
Author: Cangul, M. Z.; Chretien, Yves Rene; Gutman, R; Rubin, Donald B.

Note: Order does not necessarily reflect citation order of authors.

Citation: Cangul, M. Z., Y. R. Chretien, R. Gutman, and D. B. Rubin. 2009. Testing Treatment effects in unconfounded studies under model misspecification: Logistic regression, discretization, and their combination. Statistics in Medicine 28, no. 20: 2531–2551. doi:10.1002/sim.3633.
Access Status: Full text of the requested work is not available in DASH at this time (“dark deposit”). For more information on dark deposits, see our FAQ.
Full Text & Related Files:
Abstract: Logistic regression is commonly used to test for treatment effects in observational studies. If the distribution of a continuous covariate differs between treated and control populations, logistic regression yields an invalid hypothesis test even in an uncounfounded study if the link is not logistic. This flaw is not corrected by the commonly used technique of discretizing the covariate into intervals. A valid test can be obtained by discretization followed by regression adjustment within each interval.
Published Version: 10.1002/sim.3633
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:32095387
Downloads of this work:

Show full Dublin Core record

This item appears in the following Collection(s)

 
 

Search DASH


Advanced Search
 
 

Submitters