Assuming a constant α, tables of t were developed using the Šidák multiplicative inequality: when doing g different contrasts the familywise rate of Type 1 errors, fwi ≤ 1 − (1 − α) g . Values of t are given that yield fwi = .01, .05, .10, or .20 for number of contrasts, g = 2(1)10, 15(5)50 and degrees of freedom, v = 2(1)30, 40, 60, 120, ∞. These t values are smaller than those in the previous Dunn (1961) tables, thus yielding slightly improved power.
No takes yet. Share an insight, caveat, or question.
Paul A. Games (1977) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: