[SciPy-user] robustfit

Steve Schmerler elcorto at gmx.net
Tue Mar 8 08:45:20 CST 2005

Robert Kern wrote:
> Steve Schmerler wrote:
>> Hi developers
>> I wonder if there are plans to implement a routine in scipy.stats 
>> similar to MATLAB's robustfit() function which handels outliers in a 
>> data set by iteratively adjusting a residual weight array.
> I don't think anyone has any concrete plans to do so. Can you provide 
> any documentation about the specific algorithm you'd like to see? I've 
> encountered any number of such beasts (and don't trust any of them!).

Never mind. I ended up using Numerical Recipe's medfit() function which 
works pertty well.

Cheers, steve

There are three types of people in this world: those who make things 
happen, those who watch things happen and those who wonder what 
happened. - Mary Kay Ash

More information about the SciPy-user mailing list