[SciPy-User] Curve fit: strange documentation (josef.pktd at gmail.com)

[josef.pktd at gmail.com]

On Fri, Feb 7, 2014 at 1:37 PM, federico vaggi <vaggi.federico at gmail.com>wrote:

> In weighted least squares, the residuals are weighted by their standard
>> deviation - so it's basically the same thing.
>
>
> http://en.wikipedia.org/wiki/Weighted_least_squares#Weighted_least_squares
>
>
>
It'a not a question whether they are "basically the same thing", it's a
question of what the (imprecise) terms in the docstring actually mean.

`WLS-weights` = 1/sigma**2
but the transformation uses
w = 1/ sigma
or maybe weights just refers to general weighting, not to WLS-weights
(natural language usage instead of formal definition)

Is it squared or not, and is it the inverse or not?

sigma is the standard deviation, except it's only proportional because we
scale it (by default) with the residual standard deviation.

Josef
INALL


>
> _______________________________________________
> SciPy-User mailing list
> SciPy-User at scipy.org
> http://mail.scipy.org/mailman/listinfo/scipy-user
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.scipy.org/pipermail/scipy-user/attachments/20140207/a27335ce/attachment.html>