Online Program Home
  My Program

Abstract Details

Activity Number: 299 - Survival and Recurrent Events in Epidemiology
Type: Contributed
Date/Time: Tuesday, August 1, 2017 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistics in Epidemiology
Abstract #323342
Title: Robust Estimation in Additive Hazards Models
Author(s): Oliver Dukes* and Stijn Vansteelandt and Torben Martinussen and Eric Tchetgen Tchetgen
Companies: Ghent University and Ghent University and University of Copenhagen and Harvard University
Keywords: Causal inference ; Double Robust ; Semiparametric Estimation ; Nuisance Parameters ; Estimating Equation
Abstract:

Additive hazards models are becoming increasingly popular in survival analysis, as their parameters are collapsible and easily interpretable in terms of relative survival risks. Estimation of the effect of an exposure in such models typically demands adjustment for a high-dimensional covariate. However, misspecification of the effect of these covariates may induce large bias in the exposure effect estimate. To overcome this, we consider a novel class of semiparametric additive hazards models which leave the effects of baseline covariates unspecified. We describe two different estimators of the parameters indexing these models ; one which requires a model for the conditional expectation of the exposure at the start of the study (a.k.a the propensity score) and one which requires a model for the time-dependent propensity score. The approaches are compared via simulation studies.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association