Abstract #300990

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #300990
Activity Number: 330
Type: Contributed
Date/Time: Wednesday, August 6, 2003 : 8:30 AM to 10:20 AM
Sponsor: Section on Nonparametric Statistics
Abstract - #300990
Title: The Optimal Selection of the Number of Mass Points Through AIC in Meta-analysis
Author(s): Hideaki Watanabe*+ and Takenobu Tasaki
Companies: Shionogi & Co., LTD and Shionogi & Co., LTD
Address: 12-4 Sagisu 5-Chome Fukushima, Osaka, 553-0002, Japan
Keywords: meta-analysis ; nonparametric maximum likelihood ; mass points ; AIC
Abstract:

Meta-analysis has been widely used to establish the evidence on the efficacy of a specific treatment by synthesizing the results from a number of clinical trials. From the viewpoint of pharmaceutical companies, meta-analysis is a very useful tool to obtain the reliable estimates of efficacy variables for test drugs and/or controls including placebo. Such an estimate is essential to calculate the number of subjects required in a new clinical trial. Several approaches to meta-analysis have been proposed. We focus on non-parametric maximum likelihood (NPML) approach as an inference method to deal with random effects models that are often assumed in the context of meta-analysis. The NPML approach has some attractive features for meta-analysis. For example, it can estimate a distribution of random effects as a simple discrete distribution specified with pairs of a mass point and a mass probability. On the other hand, it seems that issues on an optimal selection of the number of mass points have not been investigated so far. We propose to use AIC to select the number of mass points and show the performances of our approach through simulation studies.

  • 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 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003