Improving the analysis of composite endpoints in rare disease trials.

ABSTRACT:

Background

Composite endpoints are recommended in rare diseases to increase power and/or to sufficiently capture complexity. Often, they are in the form of responder indices which contain a mixture of continuous and binary components. Analyses of these outcomes typically treat them as binary, thus only using the dichotomisations of continuous components. The augmented binary method offers a more efficient alternative and is therefore especially useful for rare diseases. Previous work has indicated the method may have poorer statistical properties when the sample size is small. Here we investigate small sample properties and implement small sample corrections.

Methods

We re-sample from a previous trial with sample sizes varying from 30 to 80. We apply the standard binary and

SUBMITTER: McMenamin M 

PROVIDER: S-EPMC5964664 | biostudies-literature | 2018 May

REPOSITORIES: biostudies-literature