regression software under IRIX 6.5: SUMMARY

Few days ago, I asked the following question:
 >Dear all,
 >I look for regression software (non-linear regression; works under SGI IRIX
 >6.5) I found a lot of Web sites presenting regression software that works
 >under Windows and sometimes Linux but not on IRIX 6.5 (not 5.2...)
 >I know "gnuplot" can make some regressions and I already use it
 but I would
 >like to find some other ones.
 >Moreover, if it is free for academic labs, it is better ;-)
 >Thanks, Best regards,
 Thanks to all for your answers. Here are a summary of the answers, I received:
 Groeten, David.
 Dr. David van der Spoel		Biomedical center, Dept. of Biochemistry
 s-mail:	Husargatan 3, Box 576,  75123 Uppsala, Sweden
 e-mail:	www:
 phone:	46 18 471 4205		fax: 46 18 511 755
 Have you considered xmgr
 It does regression and is free.
 Kristy Mardis
 Pacific Lutheran University
 Try the R project, a clone of S/Splus. It can do all sorts of
 regressions. Plus it's under the GPL. :-)
 -Geoff Hutchison	<>
 Ratner/Marks Groups	(847) 491-3295
 Northwestern Chemistry
 I have my own PLS code (C) for SAMPLS if you are interested? It's a
 simple command line interface. It includes crossvalidation and random
 permutation routines ...
 David Turner                                             Synt:em
 Senior Modeling Scientist              Parc Scientifique G.Besse
 Computational Drug Discovery                         30000 Nimes
 email:                                 France
 Switchboard: +33 (0)4 66 04 86 66      Fax: +33 (0)4 66 04 86 67
 Direct Line: +33 (0)4 66 04 22 85
           Discover New Drugs, Discover Synt:em
 I use R for all my statistics
 It runs on many different platforms (I've personally used it under both
 Linux and Irix, but there are also Mac and Windows versions), and it's
 a complete, modern, free (GPL) statistical computing environment.
 Some possible negative points: it may be overkill for some purposes; it
 does not have a graphical user interface; many modules are somewhat
 indigestible to the non-statistician. However, I've been very happy with
 it. The graphical capabilities are also good.
 Malcolm Gillies <>
 Post-doctoral researcher
 Organic Chemistry, Dept of Chemistry,
 Technical University of Denmark
 Dear Francois,
 did you check out
 I am not a user (yet) but the website invoked my curiosity.
 So please let me know you think it is useful for you and if you
 could compile it.
 Thanks, Best regards,
 PS: Of course I would also like to offer you help if you are
     interested in Schrödinger Software (, because
     we are the european distributeur for govermental and commercial
     institutions. Personally I do mostly Jaguar development
     (parallelization, calculation of thermodynamical properties).
        .   *       Gerd Räther   -   developer
   anteri o          Augustaanlage 26
     *        *      D-68165 Mannheim      +49 621 40041 -[t]33 -[f]40
 You may want to look at
 Ryszard Czerminski   phone: (781)994-0479
 ArQule, Inc.
 19 Presidential Way
 Woburn, MA 01801     fax: (781)994-0679
 Xmgr or the newer derivative xmgrace are able to do this. I use both on linux
 but I don't think its a problem to compile it for irix (source code is freely
 available). In my opinion xmgr is better for plotting but xmgrace is better
 for doing mathmatical operations.
 Please have a look at: .There you
 will find both programs.
 Best regards,
 PS: Please summarize your anwsers.
 F.-Y. Dupradeau