Allocation ratios

Most trials allocate equal numbers of patients to each treatment group, and for a given number of patients, maximum statistical power is (generally) obtained by allocating approximately equal numbers of patients to each treatment group.

However, power is only slightly reduced by unequal allocations such as 3 :2 and even 2 : 1 (e.g. two of every three patients randomized will be allocated the experimental treatment), as illustrated in Fig. 5.9. Why might you take advantage of this? There are a number of situations in which allocation ratios other than 1: 1 can enhance a trial, as the examples below illustrate.

0 0

Post a comment