9. Drug-Combination Trials

  1. Guosheng Yin

Published Online: 9 JAN 2012

DOI: 10.1002/9781118183335.ch9

Clinical Trial Design: Bayesian and Frequentist Adaptive Methods

Clinical Trial Design: Bayesian and Frequentist Adaptive Methods

How to Cite

Yin, G. (2011) Drug-Combination Trials, in Clinical Trial Design: Bayesian and Frequentist Adaptive Methods, John Wiley & Sons, Inc., Hoboken, NJ, USA. doi: 10.1002/9781118183335.ch9

Publication History

  1. Published Online: 9 JAN 2012
  2. Published Print: 19 DEC 2011

ISBN Information

Print ISBN: 9780470581711

Online ISBN: 9781118183335



  • continual reassessment method (CRM);
  • copula-type design;
  • drug-combination trials;
  • likelihood;
  • maximum tolerated dose (MTD);
  • sequential scheme;
  • statistical methods


This chapter covers a broad range of statistical methods for dose finding in drug-combination trials. The sequential scheme is a straightforward approach to designing a two-drug combination trial, which can be coupled with any single-agent dose-finding method. The copula-type design has an elegant structure, which reduces to the single-agent continual reassessment method (CRM) if only one drug is tested. The latent 2 x 2 table approach can easily incorporate correlations or interactions between the two drugs in combination, but the likelihood degenerates to a binomial distribution due to a lack of information on toxicities attributable to each drug. In a phase I/II drug-combination trial, the author models both toxicity and efficacy, which in fact is more natural because it need to determine the most effective one among multiple identified maximum tolerated dose (MTD) combinations due to toxicity equivalence contours.

Controlled Vocabulary Terms

copula; likelihood; sequential analysis; statistical measures