Delaware Chapter, ASA

Dinner Meeting: October 2009


Our first two meetings for the 2009-2010 year will be hosted by the University of Delaware department of Food and Resource Economics and be held in the Commons in Townsend Hall.

Subsequent meetings will be held at the Marriott Courtyard located adjacent to Clayton Hall on the University of Delaware campus.

Speaker: Richard Simon, D.Sc.
National Cancer Institute
Title: Development and Validation of Predictive Classifiers Based on High Dimensional Data Development & Use in Clinical Trial Design


Predictive classifiers are categorical functions of pre-treatment biological measurements that can be used for identifying which patients are good candidates for a specific treatment. Gene expression profiling of tumor tissue using genome-wide DNA microarrays holds great promise for the personalization of cancer therapeutics and similar opportunities exist in other disease areas. The development of predictive classifiers based on high dimensional data involves many challenges for which conventional statistical methods are ineffective. This talk will discuss some of these issues including variable selection, classifier selection, evaluating predictive accuracy and sample size determination. We will also address the issues of "classifier validation" and the use of classifiers in the design of pivotal clinical trials. Related references are listed below and reprints to these and other publications are available at --

Molinaro A, Simon R, Pfeiffer R. Prediction error estimation: A comparison of resampling methods. Bioinformatics 21:3301-3307, 2005.

Dobbin K and Simon R. Sample size planning for developing classifiers using high dimensional DNA microarray data. Biostatistics 8:101-117, 2007.

Simon R. Roadmap for developing and validating therapeutically relevant genomic classifiers. Journal of Clinical Oncology 23:7332-41, 2005.

Simon R and Maitnourim A. Evaluating the efficiency of targeted designs for randomized clinical trials. Clinical Cancer Research 10:6759-63, 2005.

Freidlin B and Simon R. Adaptive signature design: An adaptive clinical trial design for generating and prospectively testing a gene expression signature for sensitive patients. Clinical Cancer Research 11:7872-8, 2005.

Jiang W, Freidlin B, and Simon R. Biomarker adaptive threshold design: procedure for evaluating treatment with possible biomarker-defined subset effect. Journal of the National Cancer Institute 99:1036-43, 2007.

Date: Thursday, October 15, 2009

Social hour -- 6:00 pm
Dinner -- 6:30 pm
Speaker -- 7:15 pm

Townsend Hall, Commons
University of Delaware   Directions/Map

Entree: Cafeteria style
Cost: $20 form members/others, FREC students free


Reservations to: 

Irina Baldytcheva by Wednesday, October 14, 2009.
Phone: 302-885-9136
Email: Irina Baldytcheva.

Please note: Be sure to RSVP by this date.

Return to Delaware Chapter ASA home page.