BMC Medical Research Methodology

Table 3: Estimated Type I error probability of the two-stage procedure (Student’s t test or Mann-Whitney’s U test depending on preliminary Shapiro-Wilk test for normality) for different sample sizes and α _pre

From: To test or not to test: Preliminary assessment of normality when comparing two independent samples

		Strategy I					Strategy II
	α _pre	n = 10	n = 20	n = 30	n = 40	n = 50	n = 10	n = 20	n = 30	n = 40	n = 50
Exponential distribution
	.100	.050	.050	.048	.049	.048	.053	.050	.048	.049	.048
	.050	.053	.050	.048	.049	.050	.055	.052	.048	.049	.050
	.010	.054	.054	.048	.049	.050	.054	.054	.048	.049	.050
	.005	.050	.056	.050	.048	.049	.050	.055	.049	.048	.049
Uniform distribution
	.100	.049	.050	.047	.049	.049	.052	.051	.048	.049	.049
	.050	.051	.050	.050	.049	.048	.053	.051	.051	.050	.048
	.010	.051	.050	.051	.050	.051	.051	.051	.052	.051	.051
	.005	.052	.049	.049	.051	.050	.052	.050	.050	.052	.050
Normal distribution
	.100	.050	.052	.052	.051	.052	.051	.052	.053	.051	.051
	.050	.051	.051	.051	.051	.051	.051	.051	.051	.051	.050
	.010	.049	.051	.051	.051	.051	.050	.051	.051	.051	.051
	.005	.051	.050	.049	.050	.050	.051	.050	.049	.050	.050

Note: Type I error of the unconditional application of Student’s t test and Mann-Whitney’s U test is shown in Table 1 and Table 2.

Back to article page

ISSN: 1471-2288

Contact us

General enquiries: journalsubmissions@springernature.com