Nonparametric response‐adaptive randomization for continuous responses

Many response-adaptive randomization procedures have been proposed and studied over the past few decades. However, most of these procedures are based on parametric structure and do not directly apply to nonparametric models. In this paper, we propose a response-adaptive randomization procedure based on Mann-Whitney U test statistic. Under widely satisfied conditions, we derive asymptotic properties of the randomization procedure and further obtain power functions in form under Mann-Whitney U test. Simulations show the proposed procedure is more robust and more ethical than classical response-adaptive randomization procedures in some circumstances. Advantages of the procedure are also illustrated in a redesigned real clinical trial.

[1]  Feifang Hu,et al.  Immigrated urn models—theoretical properties and applications , 2008, 0812.3698.

[2]  A. R. Jonckheere,et al.  A DISTRIBUTION-FREE k-SAMPLE TEST AGAINST ORDERED ALTERNATIVES , 1954 .

[3]  William F. Rosenberger,et al.  Asymptotically best response-adaptive randomization procedures , 2006 .

[4]  Robert J Glynn,et al.  Power and sample size estimation for the clustered wilcoxon test. , 2011, Biometrics.

[5]  William F. Rosenberger,et al.  Asymptotic Inference with Response-Adaptive Treatment Allocation Designs , 1993 .

[6]  Feifang Hu,et al.  Doubly adaptive biased coin designs with delayed responses , 2008 .

[7]  N Stallard,et al.  Optimal Adaptive Designs for Binary Response Trials , 2001, Biometrics.

[8]  William F. Rosenberger,et al.  Asymptotic Properties of Adaptive designs for Clinical Trials with delayed Response , 2002 .

[9]  William F. Rosenberger,et al.  Randomization in Clinical Trials: Rosenberger/Randomization in Clinical Trials , 2016 .

[10]  William F Rosenberger,et al.  Response‐Adaptive Randomization for Clinical Trials with Continuous Outcomes , 2006, Biometrics.

[11]  S. Vansteelandt,et al.  Increasing the power of the Mann‐Whitney test in randomized experiments through flexible covariate adjustment , 2015, Statistics in medicine.

[12]  Feifang Hu,et al.  Sequential monitoring of response-adaptive randomized clinical trials with sample size re-estimation , 2010, Journal of Statistical Planning and Inference.

[13]  William F. Rosenberger,et al.  Implementing Optimal Allocation in Sequential Binary Response Experiments , 2007 .

[14]  S. Wellek.  A U‐statistics based approach to sample size planning of two‐arm trials with discrete outcome criterion aiming to establish either superiority or noninferiority , 2017, Statistics in Medicine.

[15]  Jeffrey R. Eisele.  The doubly adaptive biased coin design for sequential clinical trials , 1994 .

[16]  Vincent F. Melfi,et al.  Independence after adaptive allocation , 2008 .

[17]  Feifang Hu,et al.  Optimal Adaptive Designs for Binary Response Trials With Three Treatments , 2010 .

[18]  A. Biswas,et al.  An adaptive allocation for continuous response using Wilcoxon–Mann–Whitney score , 2004 .

[19]  L. Ruilope.  Fixed‐Combination Olmesartan/Amlodipine Was Superior to Perindopril + Amlodipine in Reducing Central Systolic Blood Pressure in Hypertensive Patients With Diabetes , 2016, Journal of clinical hypertension.

[20]  W. Rosenberger,et al.  The theory of response-adaptive randomization in clinical trials , 2006 .

[21]  William F. Rosenberger,et al.  Handling Covariates in the Design of Clinical Trials. , 2008, 1102.3773.

[22]  L. J. Wei,et al.  The Randomized Play-the-Winner Rule in Medical Trials , 1978 .

[23]  F. Hu,et al.  Interim analysis of clinical trials based on urn models , 2012 .

[24]  Feifang Hu,et al.  Efficient randomized-adaptive designs , 2009, 0908.3435.

[25]  B Rosner,et al.  Power and Sample Size Estimation for the Wilcoxon Rank Sum Test with Application to Comparisons of C Statistics from Alternative Prediction Models , 2009, Biometrics.