|
Activity Number:
|
74
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #306989 |
|
Title:
|
Methods on Longitudinal Data with Drop-Outs and Mismeasured Covariates
|
|
Author(s):
|
Grace Y. Yi*+
|
|
Companies:
|
University of Waterloo
|
|
Address:
|
200 University Ave., W., Waterloo, ON, M3G 1P3, Canada
|
|
Keywords:
|
longitudinal data ; drop-outs ; measurement error
|
|
Abstract:
|
Longitudinal data commonly contain missing observations and error-contaminated covariates. There has been quite a deal of research dealing with missingness of longitudinal studies. For example, maximum likelihood, multiple imputation, and inverse probability weighted generalized estimation equations approaches have been extensively discussed to handle missing observations. Relatively little work has been available to deal with measurement error in covariates. In this talk, I will discuss marginal methods for analyzing longitudinal data when both missingness and error-prone covariates are present. Numerical studies will be conducted with the proposed methods.
|
- 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 2006 program |
