|
Activity Number:
|
157
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 9, 2004 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
ENAR
|
| Abstract - #301859 |
|
Title:
|
Shared Random Effects Analysis of Multistate Markov Models--Application to the Nun Study
|
|
Author(s):
|
Juan C. Salazar*+ and Suzanne L. Tyas and Mark F. Desrosiers and Kathryn P. Riley and Marta S. Mendiondo and David A. Snowdon and Richard J. Kryscio
|
|
Companies:
|
University of Kentucky and University of Kentucky and University of Kentucky and University of Kentucky and University of Kentucky and University of Kentucky and University of Kentucky
|
|
Address:
|
Center on Aging, 800 South Limestone St., Lexington, KY, 40536-0230,
|
|
Keywords:
|
multistate models ; shared random effect ; polytomous logistic regression ; Markov chain ; importance sampling ; Alzheimer's disease
|
|
Abstract:
|
Multistate models are appealing tools for analyzing data about the progression of a disease over time. We consider a multistate Markov chain with two competing absorbing states (Alzheimer's disease and death) and three transient nondemented states (Cognitively Intact, Mild Cognitive Impairments, and Global Impairments). The likelihood function for the data is derived and estimates for the effects of the covariates on transitions are determined when the process can be viewed as a polytomous logistic regression model with shared random effects. The presence of a shared random effect not only complicates the formulation of the likelihood but also its evaluation and maximization. Three approaches for maximizing the likelihood are compared using a simulation study; the first method is based on the Gauss-quadrature technique, the second is based on importance sampling ideas, and the third method is based on an expansion by Taylor series. These approaches are illustrated using a longitudinal study on aging and Alzheimer's disease conducted in a population of 678 catholic sisters (The Nun Study) aged 75 to 102 when the study began in 1991.
|
