search for: iandjmsmith

...slightly surprised to find Morten's code had been included= =20 instead 2 days later. I noticed but did not worry that the reference to me = had=20 been removed.=20 The derivation of the asymptotic expansion for the gamma distribution used = by=20 Morten can be found at http://members.aol.com/iandjmsmith/PoissonApprox.htm= =20 It is fairly easy to understand and find error bounds for and hence include= =20 sensibly in an algorithm to calculate pgamma. The basis and accuracy of the some of the algorithms I use is discussed in= =20 http://members.aol.com/iandjmsmith/Accuracy.htm In this case, the ab...

Here's a contribution from Ian Smith that got bounced from the list. -------- Original Message -------- Subject: Re: [Rd] pt inaccurate when x is close to 0 (PR#9945) Date: Thu, 11 Oct 2007 06:02:43 -0400 From: iandjmsmith at aol.com To: murdoch at stats.uwo.ca Duncan, I tried sending the rest of this to R-devel but it was rejected as spam, hence the personal e-mail. R calculates the pt value from nx = 1 + (x/n)*x; val = pbeta(1./nx, n / 2., 0.5, /*lower_tail*/1, log_p); whereas Gnumeric calculates the valu...

...ould be approx 3e-308}. However, if you can get around the "licencing" problems then it would be a low risk solution to your problems. As an alternative, I offer software of mine. Code for a number of distributions, including the beta-distribution, is available at http://members.aol.com/iandjmsmith/EXAMPLES.HTM. I realise it would be a huge risk using "unknown" software but if you try the code for the beta distribution, you will find it reasonably fast, accurate and available to use any way you wish. Having downloaded the R source, I also noticed the comment /*___ FIXME ___: This...