Table 2 Test statistics
From: A simulation study for comparing testing statistics in response-adaptive randomization
Log-relative-risk | T Risk = (log(f 2 n 1/f 1 n 2))2/(r 1/n 1 f 1 + r 2/n 2 f 2) |
|---|---|
Log-odds-ratio | T Odds = (log(f 2 r 1 /f 1 r 2))2/(1/f 1 + 1/f 2 + 1/r 1 + 1/r2) |
Wald-type Z |
|
Chi-square | T Chisq = (n - 1) (r 1 f 2 - r 2 f 1)2/rfn 1 n 2 |
Log-likelihood-ratio | T LLR = 2·(r 1 log r 1 + r 2 log r 2 + f 1 log f 1 + f 2 log f 2 - r log r- f log f - n 1 log n 1 - n 2 log n 2 + n log n) |
Gart's correction to T Odds [29] | T MO = (log (f' 2 n' 1/f' 1 n' 2))2/(r' 1/n' 1 f' 1 + r' 2/n' 2 f' 2) |
Agresti's correction to T Wald |
|
Cook's correction to T Chisq | T MC = (n - 1)(|r 1 f 2 - r 2 f 1|- 0.5)2/rfn 1 n 2 |
William's correction to T LLR [31] | T ML = [1 + (n 2 - rf)(n 2 - n 1 n 2)/6rfn 1 n 2 n]-1·T LLR |
