nispace.stats.misc.meff_sidak_correction

nispace.stats.misc.meff_sidak_correction(p_array, meff, alpha=0.05, dtype=None)[source]

Sidak correction using Meff effective number of tests.

p_corr = 1 - (1 - p)^meff

Plain numpy/pandas (no numba). meff is typically obtained from compute_meff() (eigenvalue-based effective test count from a data matrix). Used in api.py as one of the available mc_method options.

Parameters:

  • p_array (array-like, DataFrame, or Series) – Uncorrected p-values.

  • meff (float) – Effective number of independent tests.

  • alpha (float, default=0.05) – Significance threshold for the reject output.

  • dtype (optional) – Cast the DataFrame/Series outputs to this dtype.

Returns:

p_corr, reject – Corrected p-values (clipped to [0, 1]) and boolean rejection mask.

Return type:

same type as p_array