(1) - nlme, lattice, stats (2) - a usable large-file/out of memory regression package that abstracts "all" the details of connections & etc from the user, accept perhaps the initial function call, so I don't have to actually know anything about the file I'm opening, how big it is, how many lines of data, how much data my system can load into memory at once without paging or crashing R, etc, but will still give me parameter estimates for multiple categorical and continuous predictors on a TB of data in less than a half hour, and can work with something more interesting than a matrix.
Sincerely, KeithC. -----Original Message----- From: Ralf B [mailto:ralf.bie...@gmail.com] Sent: Tuesday, March 02, 2010 1:14 PM To: r-help@r-project.org Subject: [R] Three most useful R package Hi R-fans, I would like put out a question to all R users on this list and hope it will create some feedback and discussion. 1) What are your 3 most useful R package? and 2) What R package do you still miss and why do you think it would make a useful addition? Pulling answers together for these questions will serve as a guide for new users and help people who just want to get a hint where to look first. Happy replying! Best, Ralf ______________________________________________ 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.