Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Docstring for NumberColumn.percentile should describe our methodology #130

Closed
onyxfish opened this issue May 31, 2014 · 2 comments
Closed

Comments

@onyxfish
Copy link
Collaborator

Because nobody seems to agree on the one true way of calculating this

@onyxfish onyxfish added this to the 0.4.0 milestone May 31, 2014
@jheasly
Copy link
Contributor

jheasly commented Jun 2, 2014

Well, the "Estimating the quantiles of a population" section of the wikipedia Quantile entry has a nice roundup of the methods, trouble is, I don't quite know how the method we're using, which comes from
http://stackoverflow.com/questions/2374640/how-do-i-calculate-percentiles-with-python-numpy/2753343#2753343 and
http://code.activestate.com/recipes/511478-finding-the-percentile-of-the-values/ maps to the wikipedia table, otherwise I'd take a whack at it.

@onyxfish
Copy link
Collaborator Author

onyxfish commented Jun 2, 2014

I think the safest description is "linear interpolation between nearest ranks", which is one method outlined in the wikipedia Percentile entry. It's sort of amazing to me that this isn't what Excel uses. (I checked yesterday and LibreOffice does something else entirely.)

@onyxfish onyxfish modified the milestone: 0.4.0 Sep 28, 2014
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants