Why are R and Python Mann Whitney different? -
i wondering why answers different when doing mann whitney u test in python , in r. in python:
from scipy.stats import mannwhitneyu t = [1,2,3] g = [4,5,6,7,8,9] mannwhitneyu(t,g) (0.0, 0.014092901073953692) in r:
t = c(1,2,3) g = c(4,5,6,7,8,9) wilcox.test(t,g, paired = false) wilcoxon rank sum test data: t , g w = 0, p-value = 0.02381 alternative hypothesis: true location shift not equal 0 i'm wondering why python 1 looks more 1 sided test.
the scipy version documented return one-sided p-value. (the doc site down me @ moment can't provide link, can see if @ mannwhitneyu function.) r function documented allow specify sidedness, two-sided default.
Comments
Post a Comment