Skip to main content

Table 3 Null simulation: empirical type-I error from 100 simulated data sets.

From: Identifying main effects and epistatic interactions from large-scale SNP data via adaptive group Lasso

Cases

Error rates per one million SNPs of different thresholds after Bonferroni correction

 

threshold = 0.1

threshold = 0.2

threshold = 0.3

Case 1

11

18

28

Case 2

3.08

4.89

7.47

  1. The nominal type-I error rates should be 10, 20, and 30 per one million SNPs for significance thresholds at 0.1, 0.2, and 0.3, respectively.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us