NONPARAMETRIC ESTIMATION OF MAXIMUM TOLERATED DOSE (MTD) IN THE CONTEXT OF PHASE Ⅰ CLINICAL TRIALS

摘要

With the advent of technology, as there seems to be no reason not to implement a trial with a continuous domain of doses and varying step sizes, we provide a non-parametric methodology for such trials that aims to estimate Maximum Tolerated Dose (MTD) in the phase I clinical trials. We further provide extensive simulations for logistic and probit models with various parameter values to obtain a pseudo sample size for better design of the trials. We also illustrate a bootstrap method to obtain an estimate of the variance and the bias of our estimator.