|
Activity Number:
|
355
- Contributed Poster Presentations: Biopharmaceutical Section
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #307108
|
|
|
Title:
|
Non-Collapsibility of Hazard Ratio
|
|
Author(s):
|
Busola Sanusi* and Godwin Yung and Yi Liu
|
|
Companies:
|
The University of North Carolina and Takeda Pharmaceuticals and Takeda Pharmaceuticals International Co.
|
|
Keywords:
|
Hazard Ratio;
Subgroups;
Treatment Efficacy
|
|
Abstract:
|
Personalized medicine aims to identify subgroups of patients who may better benefit from specific interventions as a result of their varying clinico-pathological profile. Investigators compare treatment efficacy across subgroups for the purpose of identifying patients with greater treatment benefit. However, unlike continuous and binary measures, the hazard ratio is not collapsible; the hazard ratio for an overall population need not be between the hazard ratios for two partitioning subgroups of the population. It is of interest to understand when and why this happens. We propose a general framework to study the behavior of the Cox proportional hazards model and derive theoretical results identifying scenarios in which the hazard ratio is or is not collapsible.
|
Authors who are presenting talks have a * after their name.
