mqr.inference.proportion.

power_2sample#

mqr.inference.proportion.power_2sample(p1, p2, nobs, alpha=0.05, alternative='two-sided', method='norm-approx')#

Calculate power of a test of difference of two proportions in two samples.

Null-hypothesis

p1 - p2 == 0

Parameters:
p1float

First proportion.

p2float

Second proportion.

nobsint

Number of observations.

alphafloat

Required significance.

alternative{‘two-sided’, ‘less’, ‘greater’}, optional

Sense of alternative hypothesis.

method{‘norm-approx’}, optional

Test method. Only ‘norm-approx’, the normal approximation to the binomial distribution, is implemented.

Returns:
mqr.inference.power.TestPower