263 – Contributed Poster Presentations: Biopharmaceutical Section
Comparison between Discrete and Continuous Doses for EWOC Designs
Márcio Augusto Diniz
Cedars-Sinai Medical Center
Mourad Tighiouart
Cedars-Sinai Medical Center
André Rogatko
Cedars-Sinai Medical Center
Although there is an extensive statistical literature showing the disadvantages of dichotomizing continuous variables starting with Cox (1957), categorization is a common practice in clinical research which results in substantial loss of information. A large collection of methods in cancer phase I clinical trial design defines dose of a new agent as a discrete variable. A noteworthy exception is the Escalation With Overdose Control (EWOC) design (Babb et al, 1998) where doses can be defined either as continuous or as a grid of discrete doses. A Monte Carlo simulation study was performed to compare the operating characteristics of continuous and discrete dose EWOC designs. Four equally spaced grids with different interval lengths were considered. The loss of information was measured by several operating characteristics more interpretable for clinicians in addition to the usual statistical measures of bias and mean squared error.