Journal of Medical Statistics and Informatics

Journal of Medical Statistics and Informatics

ISSN 2053-7662
Original Research

WWR: An R package for analyzing prioritized outcomes

Junshan Qiu1*, Xiaodong Luo2, Steven Bai1, Hong Tian3 and Mike Mikailov4

*Correspondence: Junshan Qiu junshan.qiu@fda.hhs.gov

1.DB1, Office of Biostatistics, Office of Translational Science, CDER, FDA, US.

Author Affiliations

2. Department of Biostatistics and Programming, Research and Development, Sanofi, US.

3. Janssen Research and Development, US.

4. Center for Device and Radiological Health, FDA, US.

Abstract

Background: In analyzing survival trials, time-to-first-event analysis is commonly used without considering clinical importance of different events. The recently proposed win loss approach can take into account the order of clinical importance of clinical events. The weighted win loss approach improves the efficiency of the original win loss approach with optimal weights. The general win loss approach can be used to handle all types of outcomes. A publically available tool to implement these approaches is on demand.

Methods: We developed an R package, WWR, to implement the win loss approaches in analyzing prioritized outcomes.

Results: We illustrate the use of this package with a real data example.

Conclusions: The WWR package provides an efficient way to calculate the win loss statistics (ratio, difference and product) and their asymptotic variances along with the contribution indexes.

Keywords: WWR, clinical trials, composite endpoints, contribution index, prioritized outcomes, variance estimation

ISSN 2053-7662
Volume 5
Abstract Download