Conditional Monte Carlo randomization tests for regression models

We discuss the computation of randomization tests for clinical trials of two treatments when the primary outcome is based on a regression model. We begin by revisiting the seminal paper of Gail, Tan, and Piantadosi (1988), and then describe a method based on Monte Carlo generation of randomization sequences. The tests based on this Monte Carlo procedure are design based, in that they incorporate the particular randomization procedure used. We discuss permuted block designs, complete randomization, and biased coin designs. We also use a new technique by Plamadeala and Rosenberger (2012) for simple computation of conditional randomization tests. Like Gail, Tan, and Piantadosi, we focus on residuals from generalized linear models and martingale residuals from survival models. Such techniques do not apply to longitudinal data analysis, and we introduce a method for computation of randomization tests based on the predicted rate of change from a generalized linear mixed model when outcomes are longitudinal. We show, by simulation, that these randomization tests preserve the size and power well under model misspecification.

[1]  M A Fischl,et al.  A randomized, controlled, double-blind study comparing the survival benefit of four different reverse transcriptase inhibitor therapies (three-drug, two-drug, and alternating drug) for the treatment of advanced AIDS. AIDS Clinical Trial Group 193A Study Team. , 1998, Journal of acquired immune deficiency syndromes and human retrovirology : official publication of the International Retrovirology Association.

[2]  B. Efron.  Forcing a sequential experiment to be balanced , 1971 .

[3]  Richard L. Smith.  Sequential Treatment Allocation Using Biased Coin Designs , 1984 .

[4]  N. Breslow.  The proportional hazards model: applications in epidemiology , 1978 .

[5]  M. H. Gail,et al.  Tests for no treatment e?ect in randomized clinical trials , 1988 .

[6]  Øyvind Langsrud,et al.  Rotation tests , 2005, Stat. Comput..

[7]  Luigi Salmaso,et al.  Permutation Tests for Complex Data , 2010 .

[8]  L. J. Wei,et al.  An Application of an Urn Model to the Design of Sequential Controlled Clinical Trials , 1978 .

[9]  V W Berger,et al.  Pros and cons of permutation tests in clinical trials. , 2000, Statistics in medicine.

[10]  William F. Rosenberger,et al.  Sequential monitoring with conditional randomization tests , 2012 .

[11]  Alessandra Giovagnoli,et al.  A new ‘biased coin design’ for the sequential allocation of two treatments , 2004 .

[12]  Ralf-Dieter Hilgers,et al.  Choice of the Reference Set in a Randomization Test Based on Linear Ranks in the Presence of Missing Values , 2012, Commun. Stat. Simul. Comput..

[13]  Daniel Commenges,et al.  Transformations which preserve exchangeability and application to permutation tests , 2003 .

[14]  Emil Frei,et al.  The Effect of 6-Mercaptopurine on the Duration of Steroid-induced Remissions in Acute Leukemia: A Model for Evaluation of Other Potentially Useful Therapy , 1963 .