Skip to content

Conversation

@changhiskhan
Copy link
Contributor

Issue #934

@jseabold
Copy link
Contributor

I just got bit by this, and I think it's a pretty serious bug. If someone will merge this, I will write some tests.

@changhiskhan
Copy link
Contributor Author

Just curious what your application is that needs population std measures?

@jseabold
Copy link
Contributor

I need sample std measures for calculating standardized (internally studentized) residuals in a linear model.

@changhiskhan
Copy link
Contributor Author

If that's the case shouldn't the default pandas behavior be correct?

@jseabold
Copy link
Contributor

No. I need sample statistics. In any event, this is a bug.

@changhiskhan
Copy link
Contributor Author

Oh, you need ddof > 1 in your use. Got it.

@jseabold
Copy link
Contributor

Yeah ddof = model degress of freedom in this case.

@Mistobaan
Copy link

+1 Need this as well

wesm added a commit that referenced this pull request Apr 2, 2012
@wesm wesm merged commit 4730ee6 into pandas-dev:master Apr 2, 2012
@wesm
Copy link
Member

wesm commented Apr 2, 2012

merged in and tested. need to update the docstrings. someday

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants