Nonparametric permutation tests for functional neuroimaging: A primer with examples

Human Brain Mapping - Tập 15 Số 1 - Trang 1-25 - 2002
Thomas E. Nichols1, Andrew P. Holmes2
1Department of Biostatistics, University of Michigan, Ann Arbor, Michigan, USA
2Robertson Centre for Biostatistics, Department of Statistics, University of Glasgow, Scotland, United Kingdom

Tóm tắt

AbstractRequiring only minimal assumptions for validity, nonparametric permutation testing provides a flexible and intuitive methodology for the statistical analysis of data from functional neuroimaging experiments, at some computational expense. Introduced into the functional neuroimaging literature by Holmes et al. ([1996]: J Cereb Blood Flow Metab 16:7–22), the permutation approach readily accounts for the multiple comparisons problem implicit in the standard voxel‐by‐voxel hypothesis testing framework. When the appropriate assumptions hold, the nonparametric permutation approach gives results similar to those obtained from a comparable Statistical Parametric Mapping approach using a general linear model with multiple comparisons corrections derived from random field theory. For analyses with low degrees of freedom, such as single subject PET/SPECT experiments or multi‐subject PET/SPECT or fMRI designs assessed for population effects, the nonparametric approach employing a locally pooled (smoothed) variance estimate can outperform the comparable Statistical Parametric Mapping approach. Thus, these nonparametric techniques can be used to verify the validity of less computationally expensive parametric approaches. Although the theory and relative advantages of permutation approaches have been discussed by various authors, there has been no accessible explication of the method, and no freely distributed software implementing it. Consequently, there have been few practical applications of the technique. This article, and the accompanying MATLAB software, attempts to address these issues. The standard nonparametric randomization and permutation testing ideas are developed at an accessible level, using practical examples from functional neuroimaging, and the extensions for multiple comparisons described. Three worked examples from PET and fMRI are presented, with discussion, and comparisons with standard parametric approaches made where appropriate. Practical considerations are given throughout, and relevant statistical concepts are expounded in appendices. Hum. Brain Mapping 15:1–25, 2001. © 2001 Wiley‐Liss, Inc.

Từ khóa


Tài liệu tham khảo

10.1073/pnas.93.18.9985

10.1097/00004647-199611000-00023

10.1002/mrm.1910350219

10.1109/42.750253

10.1239/aap/1029955192

10.1214/aoms/1177707045

10.1080/00223980.1964.9916711

10.1080/00223980.1969.10543491

Edgington ES, 1969, Statistical inference: the distribution free approach

Edgington ES, 1995, Randomization tests

Fisher RA, 1990, Bennett JH

Fisher RA, 1935, The design of experiments

10.1002/mrm.1910330508

Frackowiak RSJ, 1997, Human brain function

10.1038/jcbfm.1991.122

10.1002/hbm.460010306

10.1006/nimg.1995.1007

10.1002/hbm.460020402

10.1006/nimg.1996.0074

Good P, 1994, Permutation tests. A practical guide to resampling methods for testing hypotheses

10.1002/(SICI)1097-0193(1996)4:1<23::AID-HBM2>3.0.CO;2-R

10.1097/00004647-199710000-00004

10.1002/9780470316672

10.1097/00004647-199806000-00012

HolmesAP(1994): Statistical issues in functional brain mapping PhD thesis. University of Glasgow.http://www.fil.ion.ucl.ac.uk/spm/papers/APH_thesis

Holmes AP, 1999, Generalizability, random effects, and population inference, Neuroimage, 7, S754, 10.1016/S1053-8119(18)31587-8

10.1097/00004647-199601000-00002

10.1214/aos/1176349860

Kendal M, 1990, Rank correlation methods

LiuC RazJ TuretskyB(1998):An estimator and permutation test fro single‐trial fMRI data. In: Abstracts of ENAR meeting of the International Biometric Society. International Biometric Society.

10.1002/(SICI)1097-0193(1997)5:3<168::AID-HBM3>3.0.CO;2-1

Manly BFJ, 1997, Randomization, bootstrap, and Monte‐Carlo methods in biology

10.1162/08989290051137459

10.1016/S1053-8119(96)80036-X

Pitman EJG, 1937, Significance tests which may be applied to samples from any population, J R Stat Soc, 4, 119

Pitman EJG, 1937, Significance tests which may be applied to samples from any population. II. The correlation coefficient test, J R Stat Soc, 4, 224

Pitman EJG, 1937, Significance tests which may be applied to samples from any population. III. The analysis of variance test, Biometrika, 29, 322

10.1038/jcbfm.1993.57

10.1006/nimg.1996.0248

10.1002/hbm.460010103

10.1038/jcbfm.1994.98

10.1038/378176a0

10.1006/nimg.1999.0435

10.1016/S1053-8119(01)91602-7

10.1093/cercor/3.2.79

Westfall PH, 1993, Resampling‐based multiple testing: examples and methods for P‐value adjustment

10.2307/1427576

10.1080/01621459.1991.10475004

10.1080/09332480.1996.10542483

10.1006/nimg.1995.1023

10.1038/jcbfm.1992.127

Worsley KJ, 1995, A unified statistical approach for determining significant signals in images of cerebral activation, Hum Brain Mapp, 4, 58, 10.1002/(SICI)1097-0193(1996)4:1<58::AID-HBM4>3.0.CO;2-O

Thông tin
Thông tin xuất bản

Human Brain Mapping

Tập 15 Số 1

1-25

Thông tin tác giả