[SciPy-User] Least median of squares for regression in scipy?
Jorge Scandaliaris
jorgesmbox-ml at yahoo.es
Tue Aug 24 10:05:01 EDT 2010
Jason Rennie <jrennie <at> gmail.com> writes:
>
>
> "least median of squares" doesn't mean anything to me. But, I know that
> minimizing sum of absolute differences will provide a good estimate of the
> median and is a good technique for dealing with outliers:
>
>
>
> http://en.wikipedia.org/wiki/Least_absolute_deviation
> http://en.wikipedia.org/wiki/L1_norm
>
> Note that you'll need an LP solver. Another option is a hybrid between the
> squared and absolute value loss functions, such as the one that Peter Huber
> devised:
>
> http://en.wikipedia.org/wiki/Huber_Loss_Function
>
> This loss provides the outlier-insensitivity of L1 while being easy to solve
> using gradient descent & line search.
>
Thanks, I am not very proficient with the subject, I am just trying to use it as
a tool in a very particular task. I'll check the links you provide. BTW, this
reference is what I was taking about with "least median of squares":
http://www.stats.uwo.ca/faculty/aim/2004/04-259/ExtraReading/LeastMedianOfSquaresRegression.pdf
Regards,
Jorge
More information about the SciPy-User
mailing list