You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Carrol & Schneider (1985) suggests that the median should be used when the distribution is not known.
Carroll, R. J., & Schneider, H. (1985). A note on levene’s tests for equality of variances. Statistics & Probability Letters, 3(4), 191–194. https://doi.org/10.1016/0167-7152(85)90016-1
See the center parameter in https://docs.scipy.org/doc/scipy-0.14.0/reference/generated/scipy.stats.levene.html, and some explanation in https://en.wikipedia.org/wiki/Levene%27s_test#Comparison_with_the_Brown%E2%80%93Forsythe_test
Median is the default option in statsmodels.
See also #86 about other tests to check homogeneity.
The text was updated successfully, but these errors were encountered: