Just a remark for the future work (not part of this pull request):
for a normal distribution, the returned effect size is already normalized
for a Poisson distribution, we have to normalize it by hand
Maybe we should stick to one particular scheme and return a non-normalized effect size from the normal model (or the normalized from the Poisson model).
Just a remark for the future work (not part of this pull request):
Maybe we should stick to one particular scheme and return a non-normalized effect size from the normal model (or the normalized from the Poisson model).