Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Great point! Dividing by expected would have been a much nicer solution. I think the method I used still works though, just not as nicely. Am I wrong?


Z-Score is your friend for this kind of data normalization.

http://en.wikipedia.org/wiki/Standard_score


Thanks. It looks like I need to do a little self-study in statistics.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: