similar to: using weights in lm()

Hi! The postscript device in 0.90 does not produce symbols (pch=) as it should. E.g.: postscript(file="test.ps",width=8,height=6.4,horizontal=FALSE) plot(1:10,1:10,pch=1:5) legend(1,9,letters[1:5],pch=1:5) dev.off() The result looks quite different compared to the X-windows version. The symbol 1 (pch=1) is much to small, while the other symbols seem to big. Is it a bug? How can I

Dear R-List, I have a dataframe X containing factor f and numeric variable x1, x2, ... I want to create a new dataframe (or possibly a matrix) that gives statistics (e.g. sum) for the variables x1, x2, ... in each group defined by factor f. What is the simplest way to do this? I tried: attach(X) Z <- data.frame(f=levels(f),x1=as.vector(lapply(split(x1,f),sum))) and stumbled on: Error

From: "Wolfgang Koller" <koller2@fgr.wu-wien.ac.at> Organization: University of Economics, Vienna Date: Tue, 23 Nov 1999 16:29:22 CET (+0100) MIME-Version: 1.0 Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7BIT CC: r-bugs@biostat.ku.dk, r-help@stat.math.ethz.ch References: <153DF9230E8@fgr.wu-wien.ac.at> X-mailer: Pegasus Mail

Hi! Since installation of R 0.90 there are problems with the size of text and numbers also in the x11-device (I reported about similar problems with the postscript device recently). For numbers and letters a different size is used: plot(1:10,1:10,type="n") text(2,8,"F5F5F5F5F5") text(2,7,"F5F5F5F5F5",cex=2) The same problem is also found in the postscript

Hi! Since installation of R 0.90 there are problems with the size of text and numbers also in the x11-device (I reported about similar problems with the postscript device recently). For numbers and letters a different size is used: plot(1:10,1:10,type="n") text(2,8,"F5F5F5F5F5") text(2,7,"F5F5F5F5F5",cex=2) The same problem is also found in the postscript

Dear R-developpers, currently the function window shows the following behaviour, if start or end is out of range: > x <- ts(1:14,start=c(1950,2),frequency=4) > y <- window(x,start=c(1950,1),end=c(1953,4)) Warning messages: 1: start value not changed in: window.default(x, ...) 2: end value not changed in: window.default(x, ...) Instead of this I would like it to fill with NAs the

Dear list, I want to perform a biplot, using customized titels for the x and y axis. Setting xlab="" and ylab="" resulted in an error, e.g.: > data(USArrests) > biplot(princomp(USArrests),xlab="",ylab="") Error in biplot.default(t(t(scores[, choices])/lam), t(t(x$loadings[, : length of dimnames[1] not equal to array extent > How do I

Dear R-Users! My aim is to produce boxplots without the outliers included in the plot. I started to write a function that looks something like: myboxplot <-function(x,fa) { bpdata <- boxplot(x~fa,plot=FALSE) bpnames <- names(bpdata) for (JJ in bpnames) { command <- paste("bpdata$",JJ,"$out <- numeric(0)",sep=""); eval(command) }

Dear R-Users and Developpers, Currently R does not include functions to compute the skewness and kurtosis. I programmed it myself in the following way, but probably *real* programmers/statisticians can do that better: mykurtosis <- function(x) { m4 <- mean((x-mean(x))^4) kurt <- m4/(sd(x)^4)-3 kurt } myskewness <- function(x) { m3 <- mean((x-mean(x))^3) skew <-

Hi everyone I'm trying to generate a vector of the form a <- c(1,2,3,4,1,2,3,1,2,1) where n = 5 in a general way, where n can be any positive integer. I've run out of ideas. Does anyone have any suggestions? Thanks Karen Karen Kotschy Centre for Water in the Environment University of the Witwatersrand Johannesburg Tel: 011 716-2218

Hi everyone I'm trying to generate a vector of the form a <- c(1,2,3,4,1,2,3,1,2,1) where n = 5 in a general way, where n can be any positive integer. I've run out of ideas. Does anyone have any suggestions? Thanks Karen Karen Kotschy Centre for Water in the Environment University of the Witwatersrand Johannesburg Tel: 011 716-2218

================================================= This is an automated summary of the status of the R-bugs repository. Note that this may be neither complete nor perfectly correct at any given instance: Not all bugs are reported, and some reported bugs may have been fixed, but the repository not yet updated. Some bug fixes are difficult to verify because they pertain to specific hardware or

Dear all, first, I would like to thank R-core team for making so a great software available. Thank you all, really! Using R (1.0.0) on a Win98 platform, I need an x-server to run xgobi (through R xgobi interface). I've been using a MI/X server but trying to upgrade I noticed that MI/X is no longer available for free. Similarly, eXceed is available at evaluation version (for a limited time

>>>>> "WoKo" == Wolfgang Koller <koller2@fgr.wu-wien.ac.at> writes: WoKo> Hi! The postscript device in 0.90 does not produce symbols WoKo> (pch=) as it should. E.g.: WoKo> postscript(file="test.ps",width=8,height=6.4,horizontal=FALSE) WoKo> plot(1:10,1:10,pch=1:5) WoKo> legend(1,9,letters[1:5],pch=1:5) WoKo>

Full_Name: Wolfgang Koller Version: 1.0.0 OS: linux Submission from: (NULL) (137.208.7.48) > data(UKLungDeaths) > ts.union(mdeaths, fdeaths,dframe=TRUE) Error in names<-.default(*tmp*, value = nmsers) : names attribute must be the same length as the vector > cbind(mdeaths, fdeaths,dframe=TRUE) Error in names<-.default(*tmp*, value = nmsers) : names attribute

Hello there, I have a linear regression model for which I estimated heteroskedasticity-robust (Huber-White) standard errors using the coeftest function in the lmtest-package. Now I would like to inspect the predicted values of the dependent variable for particular groups and include a confidence interval for this prediction. My question: is it possible to estimate confidence intervals for the

The Department of Statistics and Mathematics at the Vienna University of Economics and Business Administration invites applications for two new faculty positions in computational statistics and quantitative research methodology, to begin in fall 2005. The positions will be at the Assistant level. Candidates should have a strong potential for statistical computing or intramural research support

================================================= This is an automated summary of the status of the R-bugs repository. Note that this may be neither complete nor perfectly correct at any given instance: Not all bugs are reported, and some reported bugs may have been fixed, but the repository not yet updated. Some bug fixes are difficult to verify because they pertain to specific hardware or

Dear helpers, I have strange results with levelplot: The following lines of code produce a figure with a strange gray horizontal line. Changing n to 9 the line vanishes almost - it stays in the colorbar. Any ideas? The pixel geometry of the lower half of the figure is wrong? ############################## n<-8 xyz<-expand.grid(x=seq(1,n),y=seq(1,n)) z<-matrix(0,n,n)

Hi R-helpers, I'm new to time series modelling, but my requirement seems to fall just outside the capabilities of the arima function in R. I'd like to fit an ARMA model where the variance of the disturbances is a function of some exogenous variable. So something like: Y_t = a_0 + a_1 * Y_(t-1) +...+ a_p * Y_(t-p) + b_1 * e_(t-1) +...+ b_q * e_(t-q) + e_t, where e_t ~ N(0, sigma^2_t),