Erroneous analyses of interactions in neuroscience: a problem of significance

被引：592

作者：

Nieuwenhuis, Sander ^{[1
,2
]}

Forstmann, Birte U. ^{[3
]}

Wagenmakers, Eric-Jan ^{[3
]}

机构：

[1] Leiden Univ, Dept Psychol, Leiden, Netherlands

[2] Leiden Inst Brain & Cognit, Leiden, Netherlands

[3] Univ Amsterdam, Cognit Sci Ctr Amsterdam, Amsterdam, Netherlands

来源：

NATURE NEUROSCIENCE | 2011年 / 14卷 / 09期

关键词：

D O I：

10.1038/nn.2886

中图分类号：

Q189 [神经科学];

学科分类号：

071006 ;

摘要：

In theory, a comparison of two experimental effects requires a statistical test on their difference. In practice, this comparison is often based on an incorrect procedure involving two separate tests in which researchers conclude that effects differ when one effect is significant (P < 0.05) but the other is not (P > 0.05). We reviewed 513 behavioral, systems and cognitive neuroscience articles in five top-ranking journals (Science, Nature, Nature Neuroscience, Neuron and The Journal of Neuroscience) and found that 78 used the correct procedure and 79 used the incorrect procedure. An additional analysis suggests that incorrect analyses of interactions are even more common in cellular and molecular neuroscience. We discuss scenarios in which the erroneous procedure is particularly beguiling.

引用

页码：1105 / 1107

页数：3

共 7 条

[1] Error bars in experimental biology [J].

Cumming, Geoff ;

Fidler, Fiona ;

Vaux, David L. .

JOURNAL OF CELL BIOLOGY, 2007, 177 (01) :7-11

[2] The difference between "significant" and "not significant" is not itself statistically significant [J].

Gelman, Andrew ;

Stern, Hal .

AMERICAN STATISTICIAN, 2006, 60 (04) :328-331

[3] What can functional neuroimaging tell the experimental psychologist? [J].

Henson, R .

QUARTERLY JOURNAL OF EXPERIMENTAL PSYCHOLOGY SECTION A-HUMAN EXPERIMENTAL PSYCHOLOGY, 2005, 58 (02) :193-233

[4] USING CONFIDENCE-INTERVALS IN WITHIN-SUBJECT DESIGNS [J].

LOFTUS, GR ;

MASSON, MEJ .

PSYCHONOMIC BULLETIN & REVIEW, 1994, 1 (04) :476-490

[5] Guidelines for reporting an fMRI study [J].

Poldrack, Russell A. ;

Fletcher, Paul C. ;

Henson, Richard N. ;

Worsley, Keith J. ;

Brett, Matthew ;

Nichols, Thomas E. .

NEUROIMAGE, 2008, 40 (02) :409-414

[6] THE INTERPRETATION OF LEVELS OF SIGNIFICANCE BY PSYCHOLOGICAL RESEARCHERS [J].

ROSENTHAL, R ;

GAITO, J .

JOURNAL OF PSYCHOLOGY, 1963, 55 (01) :33-38

[7] STATISTICAL PROCEDURES AND THE JUSTIFICATION OF KNOWLEDGE IN PSYCHOLOGICAL SCIENCE [J].

ROSNOW, RL ;

ROSENTHAL, R .

AMERICAN PSYCHOLOGIST, 1989, 44 (10) :1276-1284

← 1 →