Survival Analysis With Mixed Population
Xiaofei Hu, Independent consultant Sherry Xueyu Liu, CDRH, FDA *Yabing Mai, Merck Research Laboratories Tinghui Yu, FDA Keywords: bridging study, combining survival trials, misspecified models, missing data Bridging studies are used to provide treatment effect estimates of a therapeutic product based on outcome data observed from a mixed population of high heterogeneity, as such data may be collected from multiple independent clinical trials. When dealing with time-to-event data, the non-linear structure of the (log) hazard ratio estimates based on a Cox proportional hazard model leads to challenges in the development of algorithms for combining multiple clinical trials. It is of much concern that only aggregate patient data may be available in the scenario of bridging studies. In particular, if the treatment effects of the same therapeutic observed from different clinical trials of concern are known to be essentially different, one do not expect a convex combination of the hazard ratio estimates can lead to a precise description of the treatment effect among the overall population. In this talk, we proposed a combined hazard ratio estimate using aggregate data. Its asymptotic efficiency and the power of a Wald test for the combined treatment effects are demonstrated using simulations.
|
Key Dates
-
November 1 - December 17, 2013
Online proposal submission for a session, short course and Town Hall Open -
January 6 - March 11, 2014
Online proposal submission for Roundtables Open -
April 30 - May 28, 2014
Abstract Submission Open -
June 4, 2014
Online Registration Opens -
August 8 - August 22, 2014
Invited Abstract Editing -
August 11, 2014
Short Course materials due from Instructors -
September 1, 2014
Housing Deadline -
September 15, 2014
Cancellation Deadline and Registration Closes @ 11:59 pm EDT -
September 22 - September 24, 2014
Marriott Wardman Park, Washington, DC