However, when multiple assessments of hypotheses are conducted simultaneously, more than 5% of them are very likely to be statistically significant purely by chance; for example, whenmtests (here, number of genes) are performed, the experimentwise significance level will be given by 1 (1 )mmwhenis small and will represent the global Type I error rate (i
However, when multiple assessments of hypotheses are conducted simultaneously, more than 5% of them are very likely to be statistically significant purely by chance; for example,...