frites.stats.testwise_correction_mcp

frites.stats.testwise_correction_mcp(x, x_p, tail=1, mcp='maxstat')

Test-wise correction for MCP using non-parametric statistics.

This function can be used to correct the p-values for multiple comparisons at the test level (i.e at each time point, each roi, each frequencies etc.). This kind of correction usually suffers from a low statistical power (i.e if an effect is present, you might miss it because the correction is to conservative).

Parameters

xnumpy:array_like

Array of true effect

x_pnumpy:array_like

Array of permutations of shape (n_perm, …) where the other dimensions should be the same as x

tail{-1, 0, 1}

Type of comparison. Use -1 for the lower part of the distribution, 1 for the higher part and 0 for both

mcp{‘maxstat’, ‘fdr’, ‘bonferroni’}

Method to use for correcting p-values for the multiple comparison problem. By default, maximum statistics is used

Returns

pvaluesnumpy:array_like

Array of pvalues corrected for MCP with the same shape as the input x