Abstract #300286

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 #300286
Activity Number: 43
Type: Topic Contributed
Date/Time: Sunday, August 3, 2003 : 4:00 PM to 5:50 PM
Sponsor: Section on Bayesian Stat. Sciences
Abstract - #300286
Title: Hierarchical Bayesian Density Estimation for the Grid Mixture Model
Author(s): Tyson B. Rogers*+ and Robert E. Weiss
Companies: UCLA and University of California, Los Angeles
Address: 95 S Roosevelt Ave. Apt. 3, Pasadena, CA, 91107-4111,
Keywords: Bayesian ; density estimation ; mixture model ; flow cytometry ; HIV ; AIDS
Abstract:

We have a sample from an unknown density for each subject in two groups. We wish to compare the groups. This talk develops the Grid Mixture Model, a new Bayesian density estimator. Individual densities are modeled by a mixture of normal kernels with known means located on a fixed grid. The kernel weights are estimated from the data and are large in data-dense regions and small in data-sparse regions. In contrast to kernel density estimates or Dirichlet process mixture models, the Grid Mixture Model simplifies estimation by incorporating the number and locations of the kernels into the model specification. The model is applied to bivariate samples of CD-38 and HLA-DR flow cytometric measurements in two groups of HIV-infected individuals.

  • 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