RE: [R] How to suppress the printing of warnings (Windows)?
I'm a newbie in R. I am running simulations using a fixed bandwidth in nonparametric regressions, sending all the output to a file myoutput.txt using sink(myoutput.txt), R is printing all warnings by the end of the simulation on the file. I know the source of the problem can take care of it. However, finding a 50 MB file (where all the output is printed, e.g. myoutput.txt) by the end of the simulation exercise is not quite pleasant. How could I turn them off completely?, so they are not printed in myoutput.txt file. Look at ?options and scroll to 'warn.' Also, ?warnings gives an example. HTH, Andy __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] new package - paraNormal distribution
What a great package. I imagined the answer before hand, so I guess it's right... R rParaNorm(1) [1] 0+42i R This will really help me through a Bayesian analysis I have to do today. Thanks! __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] Tool for update
I think what Prof. Ripley meant is: you have to run R on a Tuesday in order to update your packages. You could lift this requirement --- and still update on Tuesdays --- by using a cron job instead. (That's assuming you're using a Unix variant, I suppose there is some equivalent way to achieve the same thing on Windows.) I'm very sorry for causing such a stir - asking What's wrong with Tuesday? was a poor attempt at humor. I was subconsciously trying to make it into the fortunes package but my wit pales in comparison to the greats. Mea culpa, Andy __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Error in save.image...recursive default argument reference
Any ideas on this one? I get the save error with compress = T also. The workspace is big. Rgui is sitting on about 300 mb of RAM. I can write objects using write.table. -Thx, Andy R save.image(lm.gs.has.run.RData) Error in save.image(lm.gs.has.run.RData) : recursive default argument reference R version _ platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major2 minor0.1 year 2004 month11 day 15 language R R __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] Tool for update
I edited Rprofile to update everything on Tuesdays. I've been doing this since 2.0 and I think I've had R running almost every Tuesday, which begs the question of what I would be doing if R hadn't come into existence. In any case, It works pretty well: ## This script gets all the packages I don't already have # Run this once a week - say Tuesdays if (interactive() ) { library(utils)} is.tuesday - as.POSIXlt(Sys.time())$wday == 2 if (is.tuesday == T) { cat(Running a package check...\nOccurs once a week, on Tuesdays\n) cat(Upgrade existing packages and check for new packages (y/N)? ) check.new - as.character(readLines(n = 1)) if (any(check.new == y, check.new == Y)) { options(CRAN = http://cran.us.r-project.org/;) cat(This can take a few seconds...\n) x - packageStatus(repositories = getOption(repositories)()[[1]]) print(x) install.packages(x$avail$Package[x$avail$Status == not installed]) cat(Upgrading to new versions if available\n) upgrade(x) } } -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Thomas Lumley Sent: Thursday, March 24, 2005 4:03 PM To: Darren Weber Cc: r-help@stat.math.ethz.ch; [EMAIL PROTECTED] Subject: Re: [R] Tool for update On Thu, 24 Mar 2005, Darren Weber wrote: Is there a way to set a cron job to automatically update packages? Maybe something like this: $unixprompt R --vanilla update.packages() If you put update.packages(repos=http://cran.us.r-project.org;, ask=FALSE) in a file update.R you can do R CMD BATCH update.R update.log or even fancier, something like R CMD BATCH update.R update-`date --iso-8601`.log to keep dated log files. -thomas __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] Tool for update
For what I understand you run this every time you use R on a Tuesday, which is not what I would want. What's wrong with Tuesday? Indeed, it's not the ideal solution but has kept me up-to-date. What has amazed me is that I think I've used R every Tuesday (and other workdays) since I did that. So, it ends up working pretty well. I will look forward to a cleaner implementation with 2.1 Much thanks, Andy __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Vogelsang test? RATS? Time series analysis.
Has anybody implemented the Vogelsang test from Vogelsang's 1998 Econometrica paper? Or the tests by Fomby and Vogelsang from their 2002 paper? I have been looking for trends in many time series (1000's) with unknown autocorrelation. In brief, I have fit AR models and classified them as stochastic or deterministic with augmented Dickey-Fuller tests. A colleague has suggested that we use a new and more elegant test that is robust to the nature of serial correlation in the residuals and pointed me the RATS program in general and Fomby and Vogelsang test in particular. Any leads appreciated, Andy ~~ Fomby TB, Vogelsang TJ, The application of size-robust trend statistics to global-warming temperature series. JOURNAL OF CLIMATE 15 (1): 117-123 2002 Vogelsang TJ, Trend function hypothesis testing in the presence of serial correlation. ECONOMETRICA 66 (1): 123-148 1998 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] R-help
This is what you are trying to get at I think: dev.off() ## start with a new graphics device # X11() or postscript() #par(mar = c(3,3,1,3), oma = c(0,0,0,0), mgp = c(2, 1, 0), bg = white) par(mar = rep(5,4)) plot(x-rnorm(100),y-rnorm(100), ylab = This is y, xlab = This is x) z-rnorm(100)*250 par(new=T) ## Tell R not to reinitialize graphic device ## for subsequent plots plot(x,z,col='blue',axes=F, xlab=, ylab=) axis(side=4,col.axis='blue', labels = T) mtext(This is z, 4, 2, col = blue) par(new=F) HTH, Andy -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Luis Ridao Cruz Sent: Tuesday, February 22, 2005 9:29 AM To: r-help@stat.math.ethz.ch Subject: [R] R-help R-help, I am tring to create a plot with two y-axis. I found an example which is fine but the problem is that the range of the second y-axes appears in the first y-axes causing confusion. The example I refer to is : ## dev.off() ## start with a new graphics device # X11() or postscript() plot(x-rnorm(100),y-rnorm(100)) z-rnorm(100)*250 par(new=T) ## Tell R not to reinitialize graphic device ## for subsequent plots plot(x,z,col='blue',axes=F) axis(side=4,col.axis='blue') par(new=F) ## which can be found at : http://www.demog.berkeley.edu/faq/node21.html I also have a home made-example with exactly the same problem (pretty much the same as above) Any solution? Thanks in advance. version _ platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major2 minor0.1 year 2004 month11 day 15 language R __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] Help about time series
?time dat - ts(rnorm(10), start = c(1900), frequency = 1) dat[time(dat) == 1905] HTH, Andy -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Ferrari Nicolas Sent: Monday, January 31, 2005 2:26 PM To: '[EMAIL PROTECTED]' Subject: [R] Help about time series Hello, When I create a ts object, I would like to get a particular value of this time serie according to the date and not the rank. However, it seems necessary to use the rank as if it were a simple vector. I would be very grateful if you could help out of this. I thank you in advance, Nicolas Ferrari __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html