SnPM - Statistical NonParametric Mapping - A toolbox for SPM
Statistical nonParametric Mapping
A toolbox for SPM
The Statistical nonParametric Mapping toolbox provides an extensible framework for non-parametric permutation/randomisation tests using the General Linear Model and pseudo t-statistics for independent observations.
- Suggestion for citing SnPM
- Citation of the SnPM software can be made with reference to this URL http://warwick.ac.uk/snpm; please also note the version (i.e. SnPM13) and the date that you last checked for updates. Concepts implemented in the SnPM software are best described in the Nichols & Holmes (2001) paper; see references below.
- The appropriate peer reviewed articles.
- The PET and fMRI example pages.
- The main SPM documentation.
- Basic non-parametric statistical texts, such as Good (1994) & Edgington (1980) will help clarify the underlying concepts of permutation/randomisation testing.
- Review the documentation above.
- Search for previous messages on the SPM email list [Jiscmail search tool] or the SnPM Google Group [link].
- Email the SnPM support email, firstname.lastname@example.org (and, if you wish, CC the SPM email list).
- Statistical Issues in functional Brain Mapping
- Holmes AP (1994)
Doctor of Philosophy Thesis, University of Glasgow, December 1994.
- Non-Parametric Analysis of Statistic Images From Functional Mapping Experiments [Pubmed]
- Holmes AP, Blair RC, Watson JDG, Ford I (1996)
Journal of Cerebral Blood Flow and Metabolism 16:7-22
- Nonparametric Analysis of PET functional Neuroimaging Experiments: A Primer [Preprint|Pubmed]
- Nichols TE, Holmes AP (2001)
Human Brain Mapping, 15:1-25.
- Holmes & Watson, on ``Sherlock'' [Preprint|Pubmed]
- Holmes & Nichols (and John Watson) reply to Halber et al.'s ``Performance of a Randomization Test for Single-Subject 15 O-Water PET Activation Studies'' published in the Journal of Cerebral Blood Flow and Metabolism
- Halber et al assert that our non-parametric approach (their implementation of which they dub `Sherlock') is less powerful than a ``standard'' analysis. This conclusion is at variance with our findings, which we consider is simply due to the fact that the ``standard analysis'' they compare to does not strongly control experimentwise Type~I error.
- Permutation inference for the general linear model
- Winkler, Ridgway, Webster, Smith & Nichols (2014). [Pubmed]
NeuroImage, 92, 381–97.
- Randomization Tests
- Edgington ES (1980)
Marcel Dekker, New York & Basel
- Permutation tests: A practical guide to resampling methods for testing hypotheses
- Good P (1994)
Springer-Verlag, New York
SnPM was originally developed by Andrew Holmes and Tom Nichols between 1995 and 1996, and Tom Nichols has led the development since 2001, with the valuable help of a number of people which we acknowledge here.
- Camille Maumet, a Post Doctoral Research Fellow at WMG, University of Warwick, completed the Matlab Batch system porting as well as various bug fixes and improvements, 2013-.
- Emma Thomas, an undergraduate student at the Department of Engineering, University of Warwick, began porting the sequential Q & A interface to the current (SPM) Matlab Batch system, 2010-2011.
- Jun Ding, University of Michigan Biostatistics, worked on the SnPM3 version, 2005-2006.
- Yanjun Xu, of the Mental Health Research Institute, University of Michigan, did important work on porting SnPM96 to Matlab 5 in 2001.
- You! Please join the SnPM development efforts on GitHub.
Deptment of Statistics
University of Warwick
Handbook of fMRI Data Analysis by Russ Poldrack, Thomas Nichols and Jeanette Mumford