Causal analysis of ordinal treatments and binary outcomes under truncation by death

TL;DR

This paper develops methods for causal analysis of ordinal treatments and binary outcomes in multiarm trials where outcomes are truncated by death, enabling joint inference under monotonicity assumptions.

Contribution

It introduces novel methods for joint and pairwise causal inference in ordinal treatment settings with binary outcomes and truncation by death, under monotonicity.

Findings

Methods enable joint inference across multiple treatment arms.

Illustrations demonstrate the applicability of assumptions in real contexts.

Appropriate for complex multiarm trial analyses with truncation issues.

Abstract

It is common that in multiarm randomized trials, the outcome of interest is "truncated by death," meaning that it is only observed or well defined conditioning on an intermediate outcome. In this case, in addition to pairwise contrasts, the joint inference for all treatment arms is also of interest. Under a monotonicity assumption we present methods for both pairwise and joint causal analyses of ordinal treatments and binary outcomes in presence of truncation by death. We illustrate via examples the appropriateness of our assumptions in different scientific contexts.