Abstract Details
Activity Number:
|
194
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 5, 2013 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Biometrics Section
|
Abstract - #309856 |
Title:
|
Doubly Robust G-Estimation for Time-Varying Outcome via the Kalman Filter
|
Author(s):
|
Sepideh Farsinezhad*+ and Masoud Asgharian and Russell J. Steele
|
Companies:
|
McGill University and McGill University and McGill University
|
Keywords:
|
Sequential randomized trial ;
Time varying confounders ;
Causation ;
Structural Nested Mean Model ;
Kalman Filtering ;
Double Robust G-Estimation
|
Abstract:
|
Doubly Robust G-Estimation is a semiparametric method of estimation developed by Robins in 2004 that adjusts for heterogeneity within individuals and over time in a sequential randomized trial. The method is consistent if either propensity score or causal model at each time point is correctly specified. For repeated measures on the outcome, specification of causal model at each time point is a concern especially when there are many time points due to time-varying confounding. In this paper, we show the utility of assuming a Markov model for the counterfactual when the subject does not receive treatment during study. In particular, we utilize Kalman filtering to help approximate the semiparametric efficient estimating function via doubly robust G-estimation. Based on our new estimating equation, analysts can avoid complicated specification of causal models at each time point, as the model for the counterfactual process summarizes the confounding by time-varying covariates.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2013 program
|
2013 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please 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.
Copyright © American Statistical Association.