Table 10.

The recommended tests.

K	TOR	Sample size design	Recommended tests
3	P1	E or WI	Benjamini–Hochberg adjusted tests
		Small AI	Dunn–Sidak adjusted BD test
		Medium or large AI	Benjamini–Hochberg adjusted BD test
	F	Small	Dunn–Sidak adjusted BD test
		Medium or large	YA test
5	P1	Small E or WI	YA test
		Medium or large E or WI	Benjamini–Hochberg adjusted tests
		Small AI	Dunn–Sidak adjusted BD test
		Medium or large AI	Benjamini–Hochberg adjusted BD test
	P2 or F	All	YA test
7	P1	Small E or WI	YA test
		Medium or large E or WI	Benjamini–Hochberg adjusted tests
		Small AI	Dunn–Sidak adjusted BD test
		Medium or large AI	Benjamini–Hochberg adjusted BD test
	P2	Small E	Chi-square-based LSD
		Small WI	Dunn–Sidak adjusted Peto test
		Small AI	Dunn–Sidak adjusted BD or Tarone test
		Medium or large	Benjamini–Hochberg adjusted BD,
			Tarone, or Woolf tests
	F	Small	BD-based LSD test
		Medium or large	YA test

Abbreviation: TOR, true odds ratio; P1, only one of the odd ratios is different; P2, more than one of the odds ratios is different, F, all the odd ratios are different; E, equal sample size design, WI, within-center inequality, AI, among-centers inequality.