Dealing with multiplicities in pharmacoepidemiologic studies

Mobile augmented reality for cultural heritage: A technology acceptance study

“…The path between PEOU and BI were significant at the p < 0.05 level. The more tests performed on the same data set, the more likely it is that one will find significant results occurring by chance (what is called the problem of multiplicity [35]). To address this we have adjusted the α-values (the probability error rate, i.e.…”

Glutathione S-transferase polymorphisms in MS

“…The hypothesis was developed a priori and significance was taken at the 0.05 level, although we accept that overall inferences could be altered by applying a multiple testing procedure such as the Bonferroni adjustment or Holm's procedure. 33 Putative high-risk genotypes for increased susceptibility or poor outcome included GSTM1 null, GSTT1 null, and GSTM3 AA. High activity GSTP1 allelic variants are dependent on the substrate under study.…”