Bayesian Sensitivity Analysis for a Missing Data Model

Bayesian Sensitivity Analysis for a Missing Data Model: Incorporating Covariates via a Cox Model

van Vliet, Christian (TU Delft Electrical Engineering, Mathematics and Computer Science)

van der Vaart, A.W. (mentor)
Krijthe, J.H. (graduation committee)

Delft University of Technology

Applied Mathematics

2023-08-02

In problems with missing data, the data are often considered to be missing at random. This assumption can not be checked from the data. We need to assess the sensitivity of study conclusions to violations of non-identifiable assumptions. This thesis performs Bayesian sensitivity analysis for a missing data model with life time outcomes and covariate information. The outcome distribution is modelled through a Cox model, with a beta process prior on the cumulative hazard function. We run experiments in a simulation study to test the performance of the model in scenarios with simulated data of several sample sizes. We show the validity of the model in the context of Bayesian sensitivity analysis, and propose extensions.

Bayesian
nonparametric
Bayesian sensitivity analysis
beta process
Cox model
survival analysis
MCMC
Dirichlet process

http://resolver.tudelft.nl/uuid:ccf7c2a5-931a-446c-9df7-f0d73dc95793

Student theses

master thesis

© 2023 Christian van Vliet