Abstract Details
Activity Number:
|
539
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 12, 2015 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistics in Epidemiology
|
Abstract #315561
|
|
Title:
|
Mitigating the Effects of Artificial Censoring in Structural Nested Failure-Time Models
|
Author(s):
|
David Vock*
|
Companies:
|
University of Minnesota
|
Keywords:
|
causal inference ;
survival analysis ;
inverse probability weighting ;
structural nested failure time models ;
G-estimation
|
Abstract:
|
Time-dependent confounding is a common problem when trying to assess the causal effect of a time-varying intervention on a time-to-event outcome. Structural nested failure time models (SNFTM) estimated by G-estimation have been proposed to overcome this problem. An inherent drawback of SNFTM estimated by G-estimation is the use of artificial censoring, a technique where some subjects who are observed to fail are treated as censored. The use of artificial censoring necessarily leads to a loss of information and reduces precision of the estimators of the structural parameters. In particular, the presence of highly unusual covariate and treatment trajectories can necessitate greater levels of artificial censoring and lead to substantial loss of information. We suggest removing subjects from follow-up once their covariate and treatment trajectories become "unusual" and then adjusting for the dependent censoring using inverse probability of censoring weighting. We discuss how to operationalize this approach and demonstrate how our method leads to improved estimation of the structural parameters.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2015 program
|
For program information, contact the JSM Registration Department or phone (888) 231-3473.
For Professional Development information, contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
2015 JSM Online Program Home
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.