R devel - Mar 2012 - Beta binomial and Beta negative binomial

Hi,
I need Beta binomial and Beta negative binomial functions but in R there is
only SuppDists package which provide this distributions using a limited
parameter space of the generalized hypergeometric distribution (dghyper &
Co.)
which provide a limited parameter space for Beta binomial and Beta negative
binomial functions (e.g. alpha + beta <1 in the Beta negative binomial).

I've done a checkout to R svn to seek the code for the implementation of
distribution functions (dbinom et al.) but I haven't succeed. I don't
know how
difficult could be to implement Beta binomial and Beta negative binomial
functions having the PDF  and CDF functions but I'm interested in
implementing
it. I have programming skills but I don't know much about R internals.

Where is the code? Can I implement these new functions inside stats
package following the
same patterns as other probability distributions?

Yours,
-- 
Joan Maspons
CREAF (Centre de Recerca Ecol?gica i Aplicacions Forestals)
Universitat Aut?noma de Barcelona, 08193 Bellaterra (Barcelona), Catalonia
Tel +34 93 581 2915 ? ? ? ? ? ?j.maspons at creaf.uab.cat
http://www.creaf.uab.cat

Hi,

Please look at the distribution task view
(http://cran.r-project.org/web/views/Distributions.html) and the package
gamlss.dist.

By the way, distributions in R are implemented in <source>/src/nmath
directory and not <source>/src/library/stats

Regards

Christophe

--
Christophe Dutang
Ph.D. student at ISFA, Lyon, France
website: http://dutangc.free.fr

Le 16 mars 2012 ? 18:41, Joan Maspons a ?crit :
> Hi,
> I need Beta binomial and Beta negative binomial functions but in R there is
> only SuppDists package which provide this distributions using a limited
> parameter space of the generalized hypergeometric distribution (dghyper
& Co.)
> which provide a limited parameter space for Beta binomial and Beta negative
> binomial functions (e.g. alpha + beta <1 in the Beta negative binomial).
> 
> I've done a checkout to R svn to seek the code for the implementation
of
> distribution functions (dbinom et al.) but I haven't succeed. I
don't know how
> difficult could be to implement Beta binomial and Beta negative binomial
> functions having the PDF  and CDF functions but I'm interested in
implementing
> it. I have programming skills but I don't know much about R internals.
> 
> Where is the code? Can I implement these new functions inside stats
> package following the
> same patterns as other probability distributions?
> 
> Yours,
> -- 
> Joan Maspons
> CREAF (Centre de Recerca Ecol?gica i Aplicacions Forestals)
> Universitat Aut?noma de Barcelona, 08193 Bellaterra (Barcelona), Catalonia
> Tel +34 93 581 2915            j.maspons at creaf.uab.cat
> http://www.creaf.uab.cat
> 
> ______________________________________________
> R-devel at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-devel