search for: robstdev

Installing R on Ubuntu 8.10, ( using sudo apt-get install r-base , and using one of the cran sites (cran.cnr.berkeley.edu)) the installation process says something about not having some gpg public key and "are you sure you want to download non-authenticated stuff [y/n]" (to which I answered yes). I'm assuming this warning can be ignored? Also: even though the Ubuntu install and

installing on Ubuntu, how to do it and have people found it to be glitchy? which is easier , binary install or from source ? With the source install, are you less likely to have a dependencies issue ? ( Ubuntu does the GCC install seamlessly, but has no mention of R )

this blog entry http://www.viggie.com/blog/software/opensuse-ubuntu-usage-experience , if credible , would seem to suggest that there is no good reason to choose Suse. I really don't have time for such nonsense, maybe I'll just reinstall as Ubuntu. Also, noticed that GCC was not installed when Suse installed. That's just weird, GCC is part of Linux. And if you try to install GCC,

Am I asking for too much: for any object that a stat proc returns ( y <- lm( y~x) , etc ) ) , is there a super convenient function like give_all_extractors( y ) that lists all extractor functions , the datatype returned , and a text descriptor field ("pairwisepval" "lsmean" etc) That would just be so convenient. What are my options for querying an object so that I can

Can't figure out how the install works, it is certainly not automatic. Also , the "Install" option on the R web site for Suse 11.1 does not work. And the install software native to Suse, cannot figure out. Does Suse have more problems installing software than Fedora or Ubuntu? Or is this a hassle for any Linux distro? And Windows? Rob [[alternative HTML version deleted]]

Hello, I have a question as to how the syntax for glht(package multcomp) and estimable (gmodels) works, since I'm not getting everything from the documents I've googled so far, especially with models with 2nd order terms. A modestly complex model: 2-way anova with one continuous covariate, no random effects(and no repeated measures) to keep it modestly complex: Y = treatmentgroup + sex