 |
 |
Kevin S. Van Horn wrote: > How about > > 1. A Linux version, even if it has to be without (or maybe even > preferably without) the GUI. > > Failing that, I'd be happy with > > 2. Source code available (under the GPL?) so that others can port it. > Agreed. Doubly. Some PhD students here have shown an interest in running WinBUGS on the laptops we have lent them. However, these laptops run Redhat 9 - with R, LaTeX, OpenOffice, etc they can do most anything they need to, and its all open source and easy for us to manage. So the WinBUGS problem. Lets attack it with Wine. I install the latest Wine rpm for Redhat 9 and get WinBUGS14.exe running (after renaming it WinBGS14.exe because wine didnt like the 'long' file name). Dialog box buttons 'almost' work. You have to click the button with the mouse and press 'Enter'. Its annoying, but at least it works. This could be related to the problem with 'blackbox'-based programs reported in the past. It seems that Wine has half-fixed it. More serious are problems with some of the statistical functionality. Some of the examples run fine, producing answers near enough to the tables in the examples. But with others, I get errors. For example, if I have 'foo[i] ~ dgamma(0.005,.5)' it runs, but change it to 'foo[i] ~ dgamma(0.004999,.5)' it fails with 'shape parameter (r) of gamma foo[1] too small -- cannot sample'. This example works fine on WinBUGS running on native Windows. This is using Wine's DLLs - I shall have another go using Windows DLLs and see if that works - but thats not a solution for those without MS Windows licenses. So, can I even trust the results output when the models seem to work? I mean, what are the Wine libraries doing? At least with the open source Wine libraries I can find out exactly what they are doing - with the closed BUGS source and the closed Windows source I have no chance. That's why I cant use BUGS personally because I cant trust the program, even under native Windows. Barry Rowlingson Maths and Stats Lancaster University Lancaster, UK ------------------------------------------------------------------- This list is for discussion of modelling issues and the BUGS software. For help with crashes and error messages, first mail [log in to unmask] To mail the BUGS list, mail to [log in to unmask] Before mailing, please check the archive at www.jiscmail.ac.uk/lists/bugs.html Please do not mail attachments to the list. To leave the BUGS list, send LEAVE BUGS to [log in to unmask] If this fails, mail [log in to unmask], NOT the whole list