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

Abstract Details

Activity Number: 534
Type: Contributed
Date/Time: Wednesday, August 4, 2010 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistical Computing
Abstract - #308171
Title: Comparison of Estimation Methods for Logistic Regression Models with Multiple Random Effects Between Statistical Packages
Author(s): Yoonsang Kim*+ and Young-Ku Choi and Sherry Emery
Companies: Institute of Health Research and Policy and Institute of Health Research and Policy and Institute of Health Research and Policy
Address: , Chicago, IL, 60608,
Keywords: Mixed-effect logistic regression ; Laplace ; penalized quasilikelihood ; Adaptive Gaussian Quadrature ; computation
Abstract:

A few statistical packages are capable of estimating generalized linear mixed models and provide at least one of three estimation methods;penalized quasilikelihood, Laplace, and adaptive Gaussian quadrature. Many studies investigated these methods and performances for the mixed-effect logistic regression model. However, they focused on models with one or two random effects and assumed somewhat simple covariance structure between them, which may not be realistic. When there are multiple random effects in a model, the computation becomes intensive and sometimes an algorithm fails to converge. To compare the performances of the three methods across statistical packages, we simulated 2-and 3-level data with at least three random effects assuming general covariance structures between random effects. Found SAS Laplace, HLM Laplace, SuperMix AGQ perform well in terms of unbiasedness and speed.


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.