Additive Bayesian Variable Selection under Censoring and Misspecification
Authors:
- 1 February 2023
- journal article
- research article
- Published by Institute of Mathematical Statistics in Statistical Science
- Vol. 38 (1) , 1-17
Abstract
We discuss the role of misspecification and censoring on Bayesian model selection in the contexts of right-censored survival and concave log-likelihood regression. Misspecification includes wrongly assuming the censoring mechanism to be noninformative. Emphasis is placed on additive accelerated failure time, Cox proportional hazards and probit models. We offer a theoretical treatment that includes local and nonlocal priors, and a general nonlinear effect decomposition to improve power-sparsity trade-offs. We discuss a fundamental question: what solution can one hope to obtain when (inevitably) models are misspecified, and how to interpret it? Asymptotically, covariates that do not have predictive power for neither the outcome nor (for survival data) censoring times, in the sense of reducing a likelihood-associated loss, are discarded. Misspecification and censoring have an asymptotically negligible effect on false positives, but their impact on power is exponential. We show that it can be advantageous to consider simple models that are computationally practical yet attain good power to detect potentially complex effects, including the use of finite-dimensional basis to detect truly nonparametric effects. We also discuss algorithms to capitalize on sufficient statistics and fast likelihood approximations for Gaussian-based survival and binary models.Keywords
All Related Versions
This publication has 52 references indexed in Scilit:
- Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problemThe Annals of Statistics, 2010
- On the use of Non-Local Prior Densities in Bayesian Hypothesis TestsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2010
- Bayesian variable selection for the analysis of microarray data with censored outcomesBioinformatics, 2006
- Effects of Model Misspecification on Tests of No Randomized Treatment Effect Arising From Cox’s Proportional Hazards ModelJournal of the Royal Statistical Society Series B: Statistical Methodology, 2001
- On a general class of semiparametric hazards regression modelsBiometrika, 2001
- Bayesian variable selection for proportional hazards modelsCanadian Journal of Statistics, 1999
- A Large Sample Study of Rank Estimation for Censored Regression DataThe Annals of Statistics, 1993
- The Robust Inference for the Cox Proportional Hazards ModelJournal of the American Statistical Association, 1989
- Effect of misspecification of regression models in the analysis of survival dataBiometrika, 1984
- Covariance Analysis of Censored Survival Data Using Log-Linear Analysis TechniquesJournal of the American Statistical Association, 1981