TY - JOUR

T1 - A Multiple Imputation Approach to Linear Regression with Clustered Censored Data

AU - Pan, Wei

AU - Connett, John E.

PY - 2001/12/1

Y1 - 2001/12/1

N2 - We extend Wei and Tanner's (1991) multiple imputation approach in semi-parametric linear regression for univariate censored data to clustered censored data. The main idea is to iterate the following two steps: 1) using the data augmentation to impute for censored failure times; 2) fitting a linear model with imputed complete data, which takes into consideration of clustering among failure times. In particular, we propose using the generalized estimating equations (GEE) or a linear mixed-effects model to implement the second step. Through simulation studies our proposal compares favorably to the independence approach (Lee et al., 1993), which ignores the within-cluster correlation in estimating the regression coefficient. Our proposal is easy to implement by using existing softwares.

AB - We extend Wei and Tanner's (1991) multiple imputation approach in semi-parametric linear regression for univariate censored data to clustered censored data. The main idea is to iterate the following two steps: 1) using the data augmentation to impute for censored failure times; 2) fitting a linear model with imputed complete data, which takes into consideration of clustering among failure times. In particular, we propose using the generalized estimating equations (GEE) or a linear mixed-effects model to implement the second step. Through simulation studies our proposal compares favorably to the independence approach (Lee et al., 1993), which ignores the within-cluster correlation in estimating the regression coefficient. Our proposal is easy to implement by using existing softwares.

KW - Asymptotic normal data augmentation

KW - Buckley-James method

KW - GEE

KW - Generalized least squares

KW - Mixed-effects model

KW - Poor Man's data augmentation

UR - http://www.scopus.com/inward/record.url?scp=0035377078&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035377078&partnerID=8YFLogxK

U2 - 10.1023/A:1011334721264

DO - 10.1023/A:1011334721264

M3 - Article

C2 - 11458652

AN - SCOPUS:0035377078

SN - 1380-7870

VL - 7

SP - 111

EP - 123

JO - Lifetime Data Analysis

JF - Lifetime Data Analysis

IS - 2

ER -