This is the mail archive of the
gsl-discuss@sources.redhat.com
mailing list for the GSL project.
Re: gsl_histogram_sum proposal
Achim Gaedke writes:
> That is a good reason - on the other hand the pdf functions have
> quite similar mechansims. The cumulative probability aspect - this
> is a scientific argument - is hit here and its my initention for
> implementing slices of the total sum.
I think the relevant quantities here are the P(x) and Q(x) functions
of the PDF. Functions to compute those would make sense. e.g.
double gsl_histogram_pdf_P (gsl_histogram_pdf *p, double x)
> I can schedule this for next week. Are there hints/ideas for
> numeric implementation (references, literature)?
The mean and sigmas should be a straightforward generalisation of
stat.c to two variables x, y. For the cross correlation use
r=<(x-<x>)(y-<y>)>/(sigma_x*sigma_y) where <.> is the weighted mean.
--
Brian
----------------------------------------------------------------------
Network Theory Ltd Phone: 0117 3179309 (+44 117 3179309)
15 Royal Park WWW: http://www.network-theory.co.uk/
Bristol BS8 3AL Email: bjg@network-theory.co.uk
United Kingdom
----------------------------------------------------------------------