|
Activity Number:
|
468
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #310173 |
|
Title:
|
Interval Estimation for the Difference in Median Survival Times Based on Multiple Imputation
|
|
Author(s):
|
Maria Kocherginsky*+ and Theodore G. Karrison
|
|
Companies:
|
The University of Chicago and The University of Chicago
|
|
Address:
|
5841 South Maryland Ave, Chicago, IL, 60637,
|
|
Keywords:
|
Survival Analysis ; Difference in Medians ; Confidence Interval ; Multiple Imputation
|
|
Abstract:
|
In survival analysis interest is often focused on the median time to event. Generation of one-sample confidence intervals for the median failure time has received considerable attention in the literature, but less attention has been given to interval estimation of the difference in medians between two groups. We propose a nonparametric method based on multiple imputation approach. Complete survival times for censored observations are first imputed by drawing from the conditional distribution given survival up to the time of censoring. The difference in medians and its variance for the complete data are then estimated using Price and Bonett (2002), and Rubin's multiple imputation procedure is used to obtain the total variance from which confidence intervals are derived. Simulations show reasonably accurate coverage probabilities for sample sizes of 25-75 per group and 10-40% censoring.
|
