This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 150
Type: Invited
Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract - #306290
Title: A Case Study of Using a Genomic Assay to Predict the Benefit of Chemotherapy in Treating Breast Cancer: Testing, Prediction, and Study Planning
Author(s): William E. Barlow*+ and Carl Yoshizawa
Companies: Cancer Research and Biostatistics (CRAB) and Genomic Health, Inc.
Address: 1730 Minor Ave, Seattle, WA, 98101,
Keywords: clinical trial ; prediction ; interaction ; biomarker
Abstract:

We describe the ability of a genomic assay to predict benefit in a randomized trial of chemotherapy. A standard approach is to test the significance of the interaction of randomized treatment with the continuous marker in combination with subset analysis. The interaction model assumes a point of equivalence after which clinical benefit for one therapy begins to emerge. Alternative models are considered though the size of the dataset leads to wide confidence limits on the estimated point of equivalence. An extension of the predictiveness curve method of Huang, Pepe, and Feng (2007) uses the marker quantiles and allows estimation of clinical benefit of chemotherapy. To confirm these results, a prospective clinical trial is planned. The linear interaction and cutpoint estimate are used to power the clinical trial, although alternative methods may provide a more consistent method.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2010 program




2010 JSM Online Program Home

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

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