Nonparametric survival analysis and vaccine efficacy using Dempster-Shafer analysis

TL;DR

This paper extends nonparametric Dempster-Shafer inference to censored data, enabling more flexible survival analysis and assessment of vaccine efficacy under different assumptions about missing data.

Contribution

It introduces a novel method for nonparametric survival analysis with censored data using Dempster-Shafer theory, applied to vaccine efficacy evaluation.

Findings

Vaccine efficacy conclusions depend on assumptions about missing data.

The method explores sensitivity of survival analysis to data independence assumptions.

Application to HIV vaccine trial demonstrates practical utility.

Abstract

We introduce an extension of nonparametric DS inference for arbitrary univariate CDFs to the case in which some failure times are (right)-censored, and then apply this to the problem of assessing evidence regarding assertions about relative risks across two populations. The approach enables exploration of the sensitivity of survival analyses to assumed independence of the missing data process and the failure proces. We present an application to the partially efficacious RV144 (HIV-1) vaccine trial, and show that the strength of conclusions of vaccine efficacy depend on assumptions about the maximum failure rates of the subjects lost-to-followup.