Thanks Robert, There have been many bug reports sent in recently - I need to add them all the tracker. Hopefully I can find time to look at your work, though it may take a while.
Thanks, Patrick On 1/28/20 4:09 AM, Janes, Robert (Columbus) via Bug reports for the GNU Scientific Library wrote: > I sent an e-mail a couple weeks ago about a fix I came up with for a problem > with the inverse Chi-squared function. The problem was in the inverse gamma > function and I suggested increasing the iteration limit to 50. That fixed > the immediate problem but then we found another problem case which this did > not fix. > > The IMSL documentation for this stated that for large degrees of freedom > after 100 iterations the code returns the present iteration value as the best > answer it can supply. I implemented this in the gamminv.c code and found > excellent agreement with IMSL when running side-by-side comparisons for > degrees of freedom from 1,000 to 32,000 in steps of 1,000. You might > consider this change over the one I suggested earlier. > > See the attached, updated source code. > > > Rob Janes > > SGS Transportation > > Senior Software Engineer > > SGS – CMX > > 2860 N. National Road Suite A > > US – 47201 – Columbus, Indiana > > Phone: +1 - 812 - 378 - 7966 > > Fax: +1 812 - 378 - 3393 > > Email: robert.ja...@sgs.com > > > > Information in this email and any attachments is confidential and intended > solely for the use of the individual(s) to whom it is addressed or otherwise > directed. Please note that any views or opinions presented in this email are > solely those of the author and do not necessarily represent those of the > Company. Finally, the recipient should check this email and any attachments > for the presence of viruses. The Company accepts no liability for any damage > caused by any virus transmitted by this email. All SGS services are rendered > in accordance with the applicable SGS conditions of service available on > request and accessible at https://www.sgs.com/en/terms-and-conditions
