frites.stats.permute_mi_trials

frites.stats.permute_mi_trials(suj, inference='rfx', n_perm=1000, random_state=None)

Generate random partitions for swapping trials.

Parameters:

sujnumpy:array_like

Array of shape (n_epochs,) used for permuting per subject

inference{‘ffx’, ‘rfx’}

Inference type (fixed or random effect)

n_permint | 1000

Number of permutations to return

random_stateint | None

Fix the random state of the machine (use it for reproducibility). If None, a random state is randomly assigned.

Returns:

y_plist

List of length (n_perm,) of random partitions for permuting trials