A tail of two sides: Artificially doubled false positive rates in neuroimaging due to the sidedness choice with t-tests.
false positive rate
family-wise error
null hypothesis significance testing
one- and two-sided testing
Journal
Human brain mapping
ISSN: 1097-0193
Titre abrégé: Hum Brain Mapp
Pays: United States
ID NLM: 9419065
Informations de publication
Date de publication:
15 02 2019
15 02 2019
Historique:
received:
24
05
2018
revised:
24
08
2018
accepted:
04
09
2018
pubmed:
29
9
2018
medline:
28
5
2020
entrez:
29
9
2018
Statut:
ppublish
Résumé
One-sided t-tests are widely used in neuroimaging data analysis. While such a test may be applicable when investigating specific regions and prior information about directionality is present, we argue here that it is often mis-applied, with severe consequences for false positive rate (FPR) control. Conceptually, a pair of one-sided t-tests conducted in tandem (e.g., to test separately for both positive and negative effects), effectively amounts to a two-sided t-test. However, replacing the two-sided test with a pair of one-sided tests without multiple comparisons correction essentially doubles the intended FPR of statements made about the same study; that is, the actual family-wise error (FWE) of results at the whole brain level would be 10% instead of the 5% intended by the researcher. Therefore, we strongly recommend that, unless otherwise explicitly justified, two-sided t-tests be applied instead of two simultaneous one-sided t-tests.
Identifiants
pubmed: 30265768
doi: 10.1002/hbm.24399
pmc: PMC6328330
mid: NIHMS992871
doi:
Types de publication
Journal Article
Research Support, N.I.H., Intramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
1037-1043Subventions
Organisme : Intramural NIH HHS
ID : Z99 MH999999
Pays : United States
Organisme : Intramural NIH HHS
ID : ZIC MH002888
Pays : United States
Organisme : Intramural NIH HHS
ID : ZIC MH002888-03
Pays : United States
Organisme : Intramural Research Programs at National Institute of Mental Heal and National Institute of Neurological Disorders and Stroke
ID : ZICMH002888
Pays : International
Commentaires et corrections
Type : CommentIn
Informations de copyright
Published 2018. This article is a U.S. Government work and is in the public domain in the USA.
Références
Neuroinformatics. 2019 Oct;17(4):515-545
pubmed: 30649677
Front Neuroinform. 2013 Jul 08;7:12
pubmed: 23847528
Neuroimage. 2017 Feb 15;147:952-959
pubmed: 27729277
Front Neuroinform. 2016 Jul 05;10:24
pubmed: 27458367
Neuroimage. 2012 Mar;60(1):747-65
pubmed: 22245637
Proc Natl Acad Sci U S A. 2016 Jul 12;113(28):7900-5
pubmed: 27357684
Neuroimage Clin. 2016 Nov 02;12:1045-1047
pubmed: 27995071
Neuroimage. 2016 Jan 1;124(Pt B):1242-1244
pubmed: 25869863
Comput Biomed Res. 1996 Jun;29(3):162-73
pubmed: 8812068
Hum Brain Mapp. 2019 Feb 15;40(3):1037-1043
pubmed: 30265768