Randomization Metrics

Jointly assessing predictability and efficiency loss in covariate adaptive randomization designs

A presentation given August 8, 2013 at the Joint Statistical Meetings in Montreal

Randomization methods generally are designed to be both unpredictable and balanced between treatment allocations overall and within strata. However, when planning studies, little consideration is given to measuring these characteristics, nor are they examined jointly, and published comparisons between methods often are not useful.

In order to compare randomization performance, we simulated various covariate-adjusted randomization methods, and compared efficiency & unpredictability graphically and statistically using proposed metrics.