Open avsmith opened 7 years ago
Hi Albert,
Thanks again for sending this patch. I finally found the time to look at it in more detail. In order to keep things a bit clean (and let the pull request only fix the actual Issue) I have taken the other parts of your commits and applied them separately on master. Could you rebase your changes on top of the current HEAD of master?
Thanks!
yup, miscommited.
P-values for T < 1.6 incorrectly calculated. Change to erfc based calculation for all T, no major performance hit detected (in limited testing).
Proposed fix for "fixes #2"