We use SAS and R here (a biostat department and consulting unit), in part because there are some things SAS does that R doesn't. In particular, we use SAS proc nlmixed with custom likelihood functions. R has similar capability but does not allow custom likelihood; the authors say adding it would be non-trivial.
I don't know how common such absolute barriers are, but they would be one thing to watch for. As others have noted, datasets too big too fit in memory are difficult in R (though the 3G barrier only applies to 32 bit hardware). If you have "customers" who themselves do data analysis, they may also resist change. I would think switching from SAS to R is a pretty big deal; it would probably be easier if you did not need to switch existing projects. Of course, that still leaves you paying some license fees. But the switch will have substantial short-term costs in time, if not money, even if users are motivated. Ross Boylan On Thu, 2009-07-16 at 17:40 -0400, Kel Lam wrote: > My institute has been heavily dependent on SAS for the past while, and > SAS is starting to charge us a very deep amount for license renewal. > Since we are a non-profit organization that is definitely not > sustainable. The team is brainstorming possibility of switching to R, > at least gradually. I am talking about the entire institute with > considerable number of analysts using SAS their entire career. > There’s a handful of us using R regularly. What kind of problems and > challenges have you faced? Any insight is much appreciated. Thank > you very much! > > Kelvin > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.