Skip to main content

Table 3 Allocation targets

From: A simulation study for comparing testing statistics in response-adaptive randomization

Optimal allocation ratio (n 1/n 2) for maximizing powers

R Risk

R Odds /R Chisq

R Wald /R Neyman

R LLR

{q 2 - p 2 exp[I 1 - I 2/(p 2 - p 1)]}/{-q 1 + p 1 exp[I 1 - I 2/(p 2 - p 1)]}

Other allocation targets

R RPW /R DL

q 2/q 1

R RSIHR

(Minimize the number of failure at fixed power of T Wald )

  1. I 1 = p 1 log(p 1) + q 1 log (q 1), I 2 = p 2 log(p 2) + q 2 log(q 2)