Search Archives

On Tue, 3 Dec 2002, Ben Bolker wrote: > It seems to make more sense to put a tiny bit of effort into > thinning the points at your end rather than building code into > R's postscript driver to deal with...

Jari Oksanen wrote: > > You need a better introductory guide! > > Than Crawley? (Was this an instant book review?) BTW, I really do not want to say anything against the book, which is excellent in my newbie's humble(?) opinion. Matej -- Matej...

On Wednesday 09 of June 2004 09:52, you wrote: > This is my first message to the list and I believe the question > I am including is a simple one. http://www.r-project.org/posting-guide.html -- Matej Cepl...

How do I get non-squared correlation coefficient in some more sensible way than sqrt(summary(lm(y~x))$r.squared)? Thanks Matej -- Matej Cepl, matej at ceplovi.cz, Finger: 89EF 4BC6 288A BF43 1BAB 25C3 E09F EF25 D964 84AC...

On Sun, Oct 27, 2002 at 01:48:26PM -0800, Thomas Lumley wrote: > Distinctly weird. Considering the price tag of SPSS I would use much stronger words, if I bought the thing myself. :-) Matej -- Matej Cepl, matej at ceplovi.cz...

Thomas Lumley wrote: > You asked R for a confidence interval for the predicted mean at x. If you > want a prediction interval at x you need interval="prediction" not > interval="confidence". Slightly OT question to this thread: How can I...

On Tue, 26 Nov 2002 ripley at stats.ox.ac.uk wrote: > You can't do linear regression with an ordered factor as a response. > If you mean to code the levels you need to do so explicitly by > codes...

Hi, I advertised gnuplot as a better alternative to the general graphing program. It came to my knowledge, that the website I have sent to this list is dead -- the correct one is http://www.gnuplot.info. Matej -- Matej Cepl...

ripley at stats.ox.ac.uk wrote: > They are not in S-PLUS. They are Crawley's own, but he does not > say where they are. Recently I managed to find them via the publisher's > web site, which links...

I have probably misunderstood something (again :-(): > CEMPLOY<-TEMPLOY[!is.na(TEMPLOY)] > sum(CEMPLOY^2/length(CEMPLOY))-mean(CEMPLOY)^2 [1] 30877.28 > var(TEMPLOY,na.rm=TRUE) [1] 30981.25 Could anybody tell me, what's going on? I suppose...

Hi, I understand that I can find t-test for the significance of the correlation coefficient on sample to population, but is there way how to make this test for more than one pair of variables together as easily as...

Hi, how to do quickly equivalent of the following? counter = 0 for(i in 1:length(data$S2)) { if(!is.na(data$S2[i])) { counter = counter + 1 } } I have imagined something like length(x,na.rm=TRUE). How can I...

On Mon, Nov 04, 2002 at 11:08:49AM +0100, Martin Maechler wrote: > Even if only subscribers could post, we would have to protect > from spam quite a bit, since many spams and even more viruses > are now spread by...

On Wednesday 16 of June 2004 21:23, Dirk Eddelbuettel wrote: > That may be related. I only recently set R_PAPERSIZE to be driven from > Debian's global paperconf setting which is supposed result in > /etc/R/Renviron having > > ## edd...

Emmanuel Paradis wrote: > Look at this post from Bill Venables. > > http://www.r-project.org/nocvs/mail/r-help/2000/4062.html > > Don't forget to look at the end of his message where he warns > if you have unequal...

On Sat, Oct 26, 2002 at 03:35:12PM -0500, Ulises Mora Alvarez wrote: > Second: After successful ./configure & make, How in the world can I > launch the R software? You should make probably also 'make install' (see INSTALL file) and...

On Thursday 22 of April 2004 08:29, Jean Eid wrote: > I just did this yesterday. you do not have an ODBC driver ( as > it says in the log). you need to (as root) use apt-get install > unixodbc and...

On Wednesday 16 of June 2004 14:42, Wolski wrote: > sqlQuery(channel, "select dir, c \ > from firsthit3 \ > where dir LIKE \"%SCHULEN%\"") Another option is paste(). This works for me (selectedCities is a constant set outside of this function): getData <- function...

ripley at stats.ox.ac.uk wrote: > or just cor(x, y). Thanks, that's it. > > > sqrt(summary(lm(y~x))$r.squared)? > > That's lost the sign, BTW. You are right, of course. Matej -- Matej Cepl, matej at ceplovi...

On Sun, Nov 10, 2002 at 11:55:46AM +0100, Milan Toth wrote: > is anybody whoo know something about making frequency tables in R. i'm > just beginner in R. thank you. The command is called table(). Hezk? den, Mat...