Authors:
(1) Yueqi Shen, Department of Biostatistics, University of North Carolina at Chapel Hill ([email protected]);
(2) Matthew A. Psioda, GSK;
(3) Joseph G. Ibrahim, Department of Biostatistics, University of North Carolina at Chapel Hill.
Table of Links
Abstract and 1 Introduction: BayesPPDSurv
2 Theoretical Framework
2.1 The Power Prior and the Normalized Power Prior
2.2 The Piecewise Constant Hazard Proportional Hazards (PWCH-PH) Model
2.3 Power Prior for the PWCH-PH Model
2.4 Implementing the Normalized Power Prior for the PWCH-PH Model
2.5 Bayesian Sample Size Determination
2.6 Data Simulation for the PWCH-PH Model
4 Case Study: Melanoma Clinical Trial Design
3.1 Sampling Priors
Our implementation in BayesPPDSurv does not assume any particular distribution for the sampling priors. The user specifies discrete approximations of the sampling priors by providing a matrix or list of parameter values and the algorithm samples with replacement from the matrix or the list as the first step of the data generation. The user must specify samp.prior.beta, a matrix of samples for β, and samp.prior.lambda, a list of matrices where each matrix represents the sampling prior for the baseline hazards for each stratum. The number of columns of each matrix must be equal to the number of intervals for that stratum.
Now we describe strategies to elicit the sampling priors, as detailed in Psioda and Ibrahim (2019). Suppose one wants to test the hypotheses
H0 : β1 ≥ 0
and
H1 : β1 < 0.
This paper is
