JSM 2014 Home
Online Program Home
My Program

Abstract Details

Activity Number: 603
Type: Contributed
Date/Time: Thursday, August 7, 2014 : 8:30 AM to 10:20 AM
Sponsor: Biometrics Section
Abstract #312867
Title: Weighted Analyses of Randomized Clinical Trials with Treatment Noncompliance and Biomarker Information Collected from a Cohort Subsample
Author(s): Shuli Li*+ and Robert J. Gray
Companies: and Dana-Farber Cancer Institute
Keywords: Cohort sampling ; Randomized trial ; Non-compliance
Abstract:

We propose methods to estimate treatment by biomarker interaction effect in a randomized clinical trial setting, where treatment non-compliance is present, and the biomarker information is only collected for a subset through a cohort sampling design. Estimators that were developed to address the non-compliance issue in our previous work and in Cuzick et al. [2007] are extended. We refer to the new methods as the doubly weighted per-protocol (DWtd PP) mehod, the weighted likelihood (WL) method and the weighted pseudo-likelihood (WPL) method. The EM algorithms proposed in our previous work are also extended to this setting. We propose a variance estimator for the WL estimator. Variances for the other two methods are estimated using non-standard bootstrap taking into account the dependence in the cohort sample (Gray [2009]). Simulations show that the WL and WPL estimators are nearly unbiased and are slightly more efficient than the DWtd PP estimator when the underlying model is correctly specified. If the underlying model is misspecified in the likelihood methods, however, the DWtd PP estimator is more robust and more efficient in estimating the interaction effect.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2014 program




2014 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Professional Development program, please contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

ASA Meetings Department  •  732 North Washington Street, Alexandria, VA 22314  •  (703) 684-1221  •  meetings@amstat.org
Copyright © American Statistical Association.