Logo

statsmodels.stats.weightstats.CompareMeans

class statsmodels.stats.weightstats.CompareMeans(d1, d2)[source]

temporary just to hold formulas

formulas should also be correct for unweighted means

not sure what happens if we have several variables. everything should go through vectorized but not checked yet.

extend to any number of groups or write a version that works in that case, like in SAS and SPSS.

Methods

std_meandiff_pooledvar() uses d1.ddof, d2.ddof which should be one for the ttest
std_meandiff_separatevar()
test_equal_var() Levene test for independence
ttest_ind([alternative, usevar]) ttest for the null hypothesis of identical means

Previous topic

statsmodels.sandbox.stats.multicomp.tiecorrect

Next topic

statsmodels.stats.weightstats.CompareMeans.std_meandiff_pooledvar

This Page