Approaches to the Problem of Type I Error in Multiple Comparisons
DOI:
https://doi.org/10.15273/dmj.Vol25No1.4435Abstract
The acceptable probability of a given statistical test showing a "false positive" result is termed the type 1 error. This is generally chosen to be 5%, meaning that one in 20 such tests would be expected to be significant by chance. When authors present a mass of significance tests the question arises as to which are "truly significant" and which represent those "one in twenty" due to chance alone. This paper discusses several approaches to this problem. These include using combined outcome measures, choosing simultaneous inference statistical tests, or applying the Bonferonni correction to a table of p-values.
Downloads
Published
1997-04-12
How to Cite
Naugler, C. T. (1997). Approaches to the Problem of Type I Error in Multiple Comparisons. DALHOUSIE MEDICAL JOURNAL, 25(1). https://doi.org/10.15273/dmj.Vol25No1.4435
Issue
Section
Original Research
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
