Abstract #301280

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 #301280
Activity Number: 63
Type: Contributed
Date/Time: Sunday, August 3, 2003 : 4:00 PM to 5:50 PM
Sponsor: Section on Statistical Computing
Abstract - #301280
Title: Comparing the Performance of Maximum Likelihood and Bayesian Methods for Latent-class Models with Covariates
Author(s): Hwan Chung*+ and Joseph L. Schafer
Companies: Pennsylvania State University and Pennsylvania State University
Address: 326 Thomas Bldg., University Park, PA, 16802-2111,
Keywords: latent-class model ; logistic regression ; maximum likelihood ; MCMC
Abstract:

The latent-class (LC) model has recently been extended to incorporate covariates as predictors of class membership through a multinomial logistic regression. Maximum likelihood (ML) has been the default method for LC analysis, and routines for ML estimation are currently available in Mplus (Muthen & Muthen 1998) and Latent Gold (Vermunt & Magidson 2000). In many examples, however, the likelihood function exhibits unusual features and likelihood-based standard errors may be unavailable or unreliable. A Bayesian approach via MCMC overcomes some of the shortcomings of ML, but introduces a difficulty of its own: the label-switching problem. We explore various issues surrounding the use of the LC model with covariates, including Bayesian alternatives to ML estimation. We formally compare the performance of ML and Bayesian methods over repeated samples by simulation, assessing the quality of point and interval estimates from ML and Bayesian methods with a variety of strategies for handling label switching.

  • 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