pingouin.power_corr

pingouin.
power_corr
(r=None, n=None, power=None, alpha=0.05, tail='twosided')[source] Evaluate power, sample size, correlation coefficient or significance level of a correlation test.
 Parameters
 rfloat
Correlation coefficient.
 nint
Number of observations (sample size).
 powerfloat
Test power (= 1  type II error).
 alphafloat
Significance level (type I error probability). The default is 0.05.
 tailstr
Indicates whether the test is “twosided” or “onesided”.
Notes
Exactly ONE of the parameters
r
,n
,power
andalpha
must be passed as None, and that parameter is determined from the others.Notice that
alpha
has a default value of 0.05 so None must be explicitly passed if you want to compute it.scipy.optimize.brenth()
is used to solve power equations for other variables (i.e. sample size, effect size, or significance level). If the solving fails, a nan value is returned.This function is a mere Python translation of the original pwr.r.test function implemented in the pwr R package. All credit goes to the author, Stephane Champely.
References
 1
Cohen, J. (1988). Statistical power analysis for the behavioral sciences (2nd ed.). Hillsdale,NJ: Lawrence Erlbaum.
 2
Examples
Compute achieved power given
r
,n
andalpha
>>> from pingouin import power_corr >>> print('power: %.4f' % power_corr(r=0.5, n=20)) power: 0.6379
Compute required sample size given
r
,power
andalpha
>>> print('n: %.4f' % power_corr(r=0.5, power=0.80, ... tail='onesided')) n: 22.6091
Compute achieved
r
givenn
,power
andalpha
level
>>> print('r: %.4f' % power_corr(n=20, power=0.80, alpha=0.05)) r: 0.5822
Compute achieved alpha level given
r
,n
andpower
>>> print('alpha: %.4f' % power_corr(r=0.5, n=20, power=0.80, ... alpha=None)) alpha: 0.1377