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

Abstract Details

Activity Number: 670
Type: Contributed
Date/Time: Thursday, August 5, 2010 : 10:30 AM to 12:20 PM
Sponsor: Biopharmaceutical Section
Abstract - #307986
Title: A Simulation Study to Evaluate Sample Size and Power for a Trial to Develop a Prediction Rule Using Machine Learning Methods
Author(s): Radha Railkar*+ and Matthew Wiener and Leonidas Carayannopoulos
Companies: Merck & Co., Inc. and Merck & Co., Inc. and Merck & Co., Inc.
Address: , , 19454,
Keywords: Prospective trials ; prediction models ; random forests ; simulation study ; sample size ; power
Abstract:

Prospective trials are rarely undertaken to develop prediction models based on a large number of variables. Prediction models are usually derived via post-hoc analyses. Data mining methods such as random forests are often used. A clinical trial was prospectively designed to develop a prediction model for response to a vaccine based on a large number of biomarkers. It was hypothesized that the coefficient of determination would be greater than a specified value. A simulation study was undertaken to evaluate the sample sizes that would be required to obtain a prediction model that would have adequate power for such a hypothesis under various assumptions regarding the number of predictor variables and the correlation structure among them. The simulation study provided valuable insight into the planning of this trial and provides guidance on the planning of future trials of this nature.


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.