Abstract #300693

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 2002 Program page
JSM 2002 Abstract #300693
Activity Number: 33
Type: Topic Contributed
Date/Time: Sunday, August 11, 2002 : 4:00 PM to 5:50 PM
Sponsor: Section on Statistical Computing*
Abstract - #300693
Title: A Multivariate Logistic Distribution for Importance Sampling
Author(s): Buffy Hudson-Curtis*+ and John Monahan and Stefanski Len
Affiliation(s): GlaxoSmithKline, Inc. and North Carolina State University and North Carolina State University
Address: Five Moore Drive PO Box 13398, Research Triangle Park, North Carolina, 27709-3398, USA
Keywords: Multivariate Logistic Distribution ; Monte Carlo Importance Sampling
Abstract:

Monte Carlo Importance sampling has been effective for computing posterior integrals in Bayesian analysis. However, much of its success depends upon the suitability of the importance sampler. A successful importance sampler will mimic the behavior of the posterior distribution--not only in the center, but also in the tails. However, both the traditional light-tailed multivariate normal importance sampler, and its alternative, the heavy-tailed multivariate-t, may not perform well for a number of posterior distributions. An alternative to these importance samplers, a generalization of the multivariate logistic distribution, is described and its advantages as an importance sampler are discussed.

  • 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 2002 program

JSM 2002

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 2002