[SciPy-user] Numerical Recipes robust fit implementation
Mon Jul 16 22:41:14 CDT 2007
Hi Anne et al.,
On 17/07/07, Anne Archibald <email@example.com> wrote:
> On 16/07/07, Angus McMorland <firstname.lastname@example.org> wrote:
> I don't know why I didn't think of this before, I've been working with
> them, but if you want to estimate a PDF (and therefore a CDF), kernel
> density estimators are a very reasonable approach. Scipy implements
> one, but if you want to include outliers you may find using a kernel
> with bigger tails than a Gaussian useful. I don't know of a robust
> kernel density estimator, but they've seen extensive work in the
> statistical literature.
I may be misunderstanding, but it looks like KDEs generate generic
pdfs based on the distribution of the observed values and not any
particular standard distribution form. I specifically need an
estimated exponential distribution to test against using the KS, since
this addresses the underlying mechanism generating the data.
Regardless, thanks for the suggestion. I'm picking up new tools left,
right and centre.
AJC McMorland, PhD Student
Physiology, University of Auckland
More information about the SciPy-user