[Rd] Re: PR#2894

tim.massingham at ebi.ac.uk tim.massingham at ebi.ac.uk
Mon Sep 22 16:49:11 MEST 2003

On Monday 22 Sep 2003 2:36 pm, I wrote:
> The 'infinite loop' is due to the speed of the pbeta routine, rather
> than the initial approximation from the qbeta. There is another
> algorithm available for pbeta (Algorithm 708, CACM 18. 360--373, 1992)

	That should be TOMS, not CACM. Sorry.

> which may be of use here. This continued fraction approximation is
> recommended by Numerical Recipes over the power series approximation
> (make of that what you will!)


More information about the R-devel mailing list