American Statistical Association
Clinical studies of anticancer therapies seek to identify predictive biomarkers by investigating whether treatment benefit differs according to biomarker status. This is, however, not straightforward when the putative biomarkers constitute high dimensional data. This talk will discuss a polygenic risk score approach to develop a one-dimensional biomarker, and examine how treatment benefit differs according to the status of this biomarker. These statistical methods are illustrated using high throughput gene expression data from an NSABP randomized trial that evaluated the addition of adjuvant trastuzumab to doxorubicin plus cyclophosphamide chemotherapy in breast cancer patients.
|Date:||Wednesday, May 31, 2017|
|Time:||4:00 - 5:00 P.M.|
Memorial Sloan Kettering Cancer Center
Department of Epidemiology and Biostatistics
485 Lexington Avenue
(Between 46th & 47th Streets)
2nd Floor, Conference Room B
New York, New York
**Outside visitors please email nearyp@mskcc for building access.
You must be on the security list to enter the floor.