Last modified: 2018-05-18
Abstract
This work deals with the problem of designing multiarm clinical trials for comparing treatments in order to achieve a compromise between the power of the classical Wald test of homogeneity of the treatment effects and ethical demands. In [5] the authors derived the target allocation maximizing the non-centrality parameter of Wald test for normal responses under a suitable ethical constraint reflecting the treatment effects. Starting from these results, in this paper we provide some important properties of this constrained optimal allocation, like e.g. its DA admissibility and its efficiency with respect to ethical and inferential criteria, taking into account estimation precision as well. Comparisons with some allocation proportions proposed in the literature are also presented.
References
1. Atkinson, A.C.: Adaptive biased-coin designs for clinical trials with several treatments. Discussiones Mathematicae Probability and Statistics 24, 85–108 (2004)
2. Azriel, D.,Mandel,M., Rinott, Y.: Optimal allocation to maximize power of two-sample tests for binary response. Biometrika 99, 101–113 (2012)
3. Baldi Antognini, A.: A theoretical analysis of the power of biased coin designs. J Stat Plan Inference 138, 1792–1798 (2008)
4. Baldi Antognini, A., Giovagnoli, A.: Compound optimal allocation for individual and collective ethics in binary clinical trials. Biometrika 97, 935–946 (2010)
5. Baldi Antognini, A., Novelli, M., Zagoraiou, M.: Optimal designs for testing hypothesis in multiarm clinical trials. Submitted.
6. Begg, C.B., Kalish, L.A.: Treatment Allocation for Nonlinear Models in Clinical Trials: The Logistic Model. Biometrics 40, 409–420 (1984)
7. Kalish, L.A., Harrington, D.P.: Efficiency of balanced treatment allocation for survival analysis. Biometrics 44, 409–420 (1988)
8. Silvey, S.D.: Optimal Designs. Chapman & Hall, London (1980)