-
-
Notifications
You must be signed in to change notification settings - Fork 132
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
The wrong skew measure? #90
Comments
I'd say mode skewness should compute the correct thing so 2. But we could keep the existing function around but with a different name, which is 1. And while you're at it, why not add Pearson's median skewness (3.)? |
I'm now leaning towards an option not on my list, computing skewness using the third standardized moment, rather than having to mess with a |
I would recommend renaming the function to something more appropriate ( I don't think inclusion of |
Okay, I made a PR #91 that adds sample skew. I wasn't sure how to sunset |
datalib currently calculates what is supposed to be Pearson's mode skewness, but does so as:
(avg - med) / std
This is non-parametric skewness, rather than:
Pearson's mode skewness which is
(avg - mode) / std
Or Pearson's median skewness, which is
3 * (avg - med) / std
So this is only giving correct values when
med == mode.
Should I:
mode
function, and then fix themodeskew
function by callingmode.
3
and rename the function to reflect that it's median skew.The text was updated successfully, but these errors were encountered: