An Extension of Continual Reassessment Method

• Activity Number: 462
• Type: Contributed
• Date/Time: Wednesday, August 3, 2011 : 8:30 AM to 10:20 AM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Xiaobin Yang*+ and Keying Ye
• Companies: The University of Texas at San Antonio and The University of Texas at San Antonio
• Keywords: Polychotomous toxicity response ; Continual reassessment method ; Latent variable ; Gibbs sampler

Abstract

Continual reassessment method (CRM) is widely used in clinical trials for fnding the maximum tolerated dose (MTD), especially in the case of dichotomized (or binary) toxicity response. By introducing a continuous latent variable we extend the CRM in the case of polychotomous (or multinomial) toxicity response. The polychotomous toxicity grades are determined according to the disjoint intervals in which the latent variable falls. We first introduce the latent variables in the case of dichotomized toxicity response. Compared with the traditional CRM, the method with latent variable is applicable and comparable based on the simulation studies. Then we apply the method with latent variable in the case of polychotomous toxicity response. The joint posterior distribution and the fully conditional distributions of the parameters are obtained. Furthermore, simulation studies using the Gibbs sampler in the case of polychotomous toxicity response will be given.