mne.stats.permutation_cluster_test¶

mne.stats.
permutation_cluster_test
(X, threshold=None, n_permutations=1024, tail=0, stat_fun=None, adjacency=None, n_jobs=1, seed=None, max_step=1, exclude=None, step_down_p=0, t_power=1, out_type=None, check_disjoint=False, buffer_size=1000, connectivity=None, verbose=None)[source]¶ Clusterlevel statistical permutation test.
For a list of
NumPy arrays
of data, calculate some statistics corrected for multiple comparisons using permutations and clusterlevel correction. Each element of the listX
should contain the data for one group of observations (e.g., 2D arrays for time series, 3D arrays for timefrequency power values). Permutations are generated with random partitions of the data. See 1 for details. Parameters
 X
list
ofarray
, shape (n_observations, p[, q]) The data to be clustered. Each array in
X
should contain the observations for one group. The first dimension of each array is the number of observations from that group; remaining dimensions comprise the size of a single observation. For example ifX = [X1, X2]
withX1.shape = (20, 50, 4)
andX2.shape = (17, 50, 4)
, thenX
has 2 groups with respectively 20 and 17 observations in each, and each data point is of shape(50, 4)
. Note: that the last dimension of each element ofX
should correspond to the dimension represented in theadjacency
parameter (e.g., spectral data should be provided as(observations, frequencies, channels/vertices)
). threshold
float
dict
None
If numeric, vertices with data values more extreme than
threshold
will be used to form clusters. If threshold isNone
, an Fthreshold will be chosen automatically that corresponds to a pvalue of 0.05 for the given number of observations (only valid when using an Fstatistic). Ifthreshold
is adict
(with keys'start'
and'step'
) then thresholdfree cluster enhancement (TFCE) will be used (see the TFCE example and 2). n_permutations
int
The number of permutations to compute.
 tail
int
If tail is 1, the statistic is thresholded above threshold. If tail is 1, the statistic is thresholded below threshold. If tail is 0, the statistic is thresholded on both sides of the distribution.
 stat_fun
callable()
None
Function called to calculate the test statistic. Must accept 1Darray as input and return a 1D array. If
None
(the default), usesmne.stats.f_oneway()
. adjacency
scipy.sparse.spmatrix
None
False
Defines adjacency between locations in the data, where “locations” can be spatial vertices, frequency bins, etc. If
False
, assumes no adjacency (each location is treated as independent and unconnected). IfNone
, a regular lattice adjacency is assumed, connecting each location to its neighbor(s) along the last dimension of each groupX[k]
(or the last two dimensions ifX[k]
is 2D). Ifadjacency
is a matrix, it is assumed to be symmetric (only the upper triangular half is used) and must be square with dimension equal toX[k].shape[1]
orX[k].shape[1] * X[k].shape[2]
. n_jobs
int
The number of jobs to run in parallel (default 1). Requires the joblib package.
 seed
None
int
 instance ofRandomState
If
seed
is anint
, it will be used as a seed forRandomState
. IfNone
, the seed will be obtained from the operating system (seeRandomState
for details). Default isNone
. max_step
int
Maximum distance along the second dimension (typically this is the “time” axis) between samples that are considered “connected”. Only used when
connectivity
has shape (n_vertices, n_vertices). excludebool
array
orNone
Mask to apply to the data to exclude certain points from clustering (e.g., medial wall vertices). Should be the same shape as X. If None, no points are excluded.
 step_down_p
float
To perform a stepdowninjumps test, pass a pvalue for clusters to exclude from each successive iteration. Default is zero, perform no stepdown test (since no clusters will be smaller than this value). Setting this to a reasonable value, e.g. 0.05, can increase sensitivity but costs computation time.
 t_power
float
Power to raise the statistical values (usually Fvalues) by before summing (sign will be retained). Note that
t_power=0
will give a count of locations in each cluster,t_power=1
will weight each location by its statistical score. out_type‘mask’  ‘indices’
Output format of clusters. If
'mask'
, returns boolean arrays the same shape as the input data, withTrue
values indicating locations that are part of a cluster. If'indices'
, returns a list of lists, where each sublist contains the indices of locations that together form a cluster. Note that for large datasets,'indices'
may use far less memory than'mask'
. The default translates to'mask'
in version 0.21 but will change to'indices'
in version 0.22. check_disjointbool
Whether to check if the connectivity matrix can be separated into disjoint sets before clustering. This may lead to faster clustering, especially if the second dimension of
X
(usually the “time” dimension) is large. buffer_size
int
None
Block size to use when computing test statistics. This can significantly reduce memory usage when n_jobs > 1 and memory sharing between processes is enabled (see
mne.set_cache_dir()
), becauseX
will be shared between processes and each process only needs to allocate space for a small block of locations at a time. connectivity
None
Deprecated and will be removed in 0.22, use
adjacency
instead. verbosebool,
str
,int
, orNone
If not None, override default verbose level (see
mne.verbose()
and Logging documentation for more). If used, it should be passed as a keywordargument only.
 X
 Returns
References
 1
Eric Maris and Robert Oostenveld. Nonparametric statistical testing of EEG and MEGdata. Journal of Neuroscience Methods, 164(1):177–190, 2007. doi:10.1016/j.jneumeth.2007.03.024.
 2
Stephen M. Smith and Thomas E. Nichols. Thresholdfree cluster enhancement: addressing problems of smoothing, threshold dependence and localisation in cluster inference. NeuroImage, 44(1):83–98, 2009. doi:10.1016/j.neuroimage.2008.03.061.