|
Activity Number:
|
74
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #306008 |
|
Title:
|
A Multiple Imputation Approach for Responders Analysis in Longitudinal Studies
|
|
Author(s):
|
Liqiu Jiang*+ and Kaifeng Lu and Anastasios A. Tsiatis
|
|
Companies:
|
North Carolina State University and Merck & Co., Inc. and North Carolina State University
|
|
Address:
|
1506 Ashley Downs Drive, Apex, NC, 27502,
|
|
Keywords:
|
missing data ; multiple imputation ; repeated measures ; logistic regression
|
|
Abstract:
|
Often a binary variable is generated by dichotomizing an underlying continuous measurement. Ordinarily, a logistic regression model is used to estimate the effects of covariates on the binary response. When the underlying continuous measurements are from a longitudinal study, the repeated measurements are often analyzed using a repeated measures model. This motivates us to use repeated measures model as an imputation approach in the presence of missing data on the responder status. We, then, apply the logistic regression model on the observed or otherwise imputed responder status. Large sample properties of the estimators are derived and simulation studies carried out to assess the performance of the estimators in situations where either the imputation model or the response model is misspecified. We show that the estimators are robust to misspecification.
|
