mne.stats.
permutation_cluster_1samp_test
(X, threshold=None, n_permutations=1024, tail=0, stat_fun=<function ttest_1samp_no_p>, connectivity=None, verbose=None, n_jobs=1, seed=None, max_step=1, exclude=None, step_down_p=0, t_power=1, out_type='mask', check_disjoint=False, buffer_size=1000)[source]¶Non-parametric cluster-level 1 sample T-test.
From a array of observations, e.g. signal amplitudes or power spectrum estimates etc., calculate if the observed mean significantly deviates from 0. The procedure uses a cluster analysis with permutation test for calculating corrected p-values. Randomized data are generated with random sign flips. See [R173173] for more information.
Parameters: | X : array, shape=(n_samples, p, q) or (n_samples, p)
threshold : float | dict | None
n_permutations : int
tail : -1 or 0 or 1 (default = 0)
stat_fun : function
connectivity : sparse matrix or None
verbose : bool, str, int, or None
n_jobs : int
seed : int | instance of RandomState | None
max_step : int
exclude : boolean array or None
step_down_p : float
t_power : float
out_type : str
check_disjoint : bool
buffer_size: int or None
|
---|---|
Returns: | T_obs : array, shape (n_tests,)
clusters : list
cluster_pv : array
H0 : array, shape (n_permutations,)
|
Notes
If n_permutations >= 2 ** (n_samples - (tail == 0))
,
n_permutations
and seed
will be ignored since an exact test
(full permutation test) will be performed.
If no initial clusters are found, i.e., all points in the true
distribution are below the threshold, then clusters
, cluster_pv
,
and H0
will all be empty arrays.
References
[R173173] | (1, 2) Maris/Oostenveld (2007), “Nonparametric statistical testing of EEG- and MEG-data” Journal of Neuroscience Methods, Vol. 164, No. 1., pp. 177-190. doi:10.1016/j.jneumeth.2007.03.024. |
mne.stats.permutation_cluster_1samp_test
¶