Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 295 - Causal, Robust, and Machine Learning for Survival Outcomes
Type: Invited
Date/Time: Wednesday, August 11, 2021 : 3:30 PM to 5:20 PM
Sponsor: Lifetime Data Science Section
Abstract #317022
Title: Assumption-Lean Inference for Cox Regression Parameters
Author(s): Stijn Vansteelandt* and Oliver Dukes and Kelly Van Lancker
Companies: Ghent University and Ghent University and Ghent University, Belgium
Keywords: causal inference; machine learning; targeted learning; Cox regression; variable selection

Inference for the parameters indexing Cox regression models is routinely based on the assumption that the model is correct and a priori specified. This is unsatisfactory because the chosen model is usually the result of a data-adaptive model selection process, which induces bias and excess uncertainty that is not usually acknowledged; moreover, the assumptions encoded in the resulting model rarely represent some a priori known, ground truth. Standard inferences may therefore lead to bias in effect estimates, and may moreover fail to give a pure reflection of the information that is contained in the data. Inspired by developments on assumption-free inference for so-called projection parameters, we here propose nonparametric definitions of main effect estimands which reduce to standard main effect parameters in Cox regression models when these models are correctly specified, but continue to capture the primary (conditional) association between a variable and an event time, even when these models are misspecified. We achieve an assumption-lean inference for these estimands by deriving their influence curve under the nonparametric model and invoking flexible data-adaptive algorithms.

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

Back to the full JSM 2021 program