Activity Number:
|
199
|
Type:
|
Topic Contributed
|
Date/Time:
|
Tuesday, August 13, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Health Policy Statistics*
|
Abstract - #300647 |
Title:
|
Analyses for Handling Non-random Missing Data and Censorship by Death in Longitudinal Quality of Life Studies for Advanced-Stage Disease
|
Author(s):
|
Donna Pauler*+ and Sheryl Giarritta and Carol Moinpour
|
Affiliation(s):
|
Fred Hutchinson Cancer Research Center and Fred Hutchinson Cancer Research Center and Fred Hutchinson Cancer Research Center
|
Address:
|
1100 Fairview Ave N, MP-557, Seattle, Washington, 98109-1024, USA
|
Keywords:
|
quality of life ; informative drop-out ; joint models ; sensitivity analysis ; longitudinal data
|
Abstract:
|
Analyses of longitudinal quality of life (QOL) for patients with advanced-stage disease are frequently plagued by problems of non-random drop-out attributable to deteriorating health and/or death. In this talk we examine exploratory and inferential techniques for longitudinal QOL data subject to nonrandom missingness of both types. We propose a joint model for estimating the average treatment effect on longitudinal QOL, which allows for adjustment for informative drop-out and censorship by death, straightforward implementation of sensitivity analyses, and explicit comparisons to the raw data. In addition, we outline a sensitivity analysis for the counterfactual treatment effect on QOL in the group of patients who would have completed follow-up under both treatments. We illustrate our methods in an assessment of QOL for patients treated for advanced-stage colorectal cancer in a clinical trial of several chemotheraupetic regimes (Moinpour et. al., Psycho-oncology 9:340-354, 2000).
|