statsmodels.stats.oneway.power_equivalence_oneway¶

statsmodels.stats.oneway.power_equivalence_oneway(f2_alt, equiv_margin, nobs_t, n_groups=None, df=None, alpha=0.05, margin_type='f2')[source]¶

Power of oneway equivalence test

Parameters:¶

f2_alt : float¶

Effect size, squared Cohen’s f, under the alternative.

equiv_margin : float¶

Equivalence margin in terms of effect size. Effect size can be chosen with margin_type. default is squared Cohen’s f.

nobs_t : ndarray¶

Total number of observations summed over all groups.

n_groups : int¶

Number of groups in oneway comparison. If margin_type is “wellek”, then either n_groups or df has to be given.

df : tuple¶

Degrees of freedom for F distribution, df = (n_groups - 1, nobs_t - n_groups)

alpha : float in (0, 1)¶

Significance level for the hypothesis test.

margin_type : "f2" or "wellek"¶

Type of effect size used for equivalence margin, either squared Cohen’s f or Wellek’s psi. Default is “f2”.

Returns:¶

pow_alt – Power of the equivalence test at given equivalence effect size under the alternative.

Return type:¶

float