This is the mail archive of the
gsl-discuss@sources.redhat.com
mailing list for the GSL project.
Re: gsl-chisquare cumulative density function
- To: Gilles Frising <frising at mail dot desy dot de>
- Subject: Re: gsl-chisquare cumulative density function
- From: Brian Gough <bjg at network-theory dot co dot uk>
- Date: Tue, 25 Sep 2001 19:12:12 +0100 (BST)
- Cc: gsl-discuss at sources dot redhat dot com
- References: <3BB0B7C4.3F71BBF8@mail.desy.de>
Gilles Frising writes:
> I wanted to use the cumulative chisquare pdf of gsl:
> `gsl_ran_chisq_pdf'. I checked this function in maple,cernlib and
> gsl, and i found different result for gsl.
>
> MAPLE:
> statevalf[cdf,chisquare[6]](3.);
> .1911531695
>
> CERNLIB:
> prob: 0.191153
>
> GSL:
> gsl_ran_chisq_pdf(3.,6.): 0.125511
> =========
>
> Is this a bug or have i done sth. wrong?
Hi,
The pdf is the probability distribution function (point value), so
this is a different quantity from the cdf.
The cumulative cdf's are not implemented in the present version of
GSL. We are looking for a volunteer to write them.
In the meantime you'd have to look up the formula and use the
corresponding routines from the specfunc directory -- it's an
incomplete gamma function, I believe.
regards
Brian Gough