similar to: cut with infinite values -> NA

You are correct in your expectations. This is a bug: the C code does not cover the cases +/-Inf (because it uses R_FINITE to exclude them). I'll fix it in R-patched: filing with R-bugs for the record. On 20 Jun 2002, Markus [ISO-8859-1] Jäntti wrote: > I am doing work on changes in establishment sizes and came across > behavior that is quite understandable and easily worked around

Dear list: since it took me a little while to figure out how to make use of naresid, I thought that the below R code might be useful as an example on the help page. Regards, Markus # generate some data x1 <- runif(20) y <- 10 + 5*x1 + rnorm(20) summary(lm.0 <- lm(y ~ x1)) # append some NA's to y y <- c(y, rep(NA, 5)) # generate some further x1s x1 <- c(x1, runif(5)) #

Dear list: since it took me a little while to figure out how to make use of naresid, I thought that the below R code might be useful as an example on the help page. Regards, Markus # generate some data x1 <- runif(20) y <- 10 + 5*x1 + rnorm(20) summary(lm.0 <- lm(y ~ x1)) # append some NA's to y y <- c(y, rep(NA, 5)) # generate some further x1s x1 <- c(x1, runif(5)) #

I am having some trouble getting reftex, in particular the bibtex related features, to work properly in xemacs when editing text in Sweave files. I have added (defun Rnw-mode () (noweb-mode) (if (fboundp 'R-mode) (setq noweb-default-code-mode 'R-mode))) (add-to-list 'auto-mode-alist '("\\.Rnw\\'" . Rnw-mode)) (add-to-list 'auto-mode-alist

This smells like a bug to me. The error is triggered by the line: variables <- eval(predvars, data, env) inside model.frame.default(). At that point, na.action has not been applied, so poly() ended being called on data that still contains missing values. The qr() that issued the error is for generating the orthogonal basis when evaluating poly(), not for fitting the linear model itself.

This smells like a bug to me. The error is triggered by the line: variables <- eval(predvars, data, env) inside model.frame.default(). At that point, na.action has not been applied, so poly() ended being called on data that still contains missing values. The qr() that issued the error is for generating the orthogonal basis when evaluating poly(), not for fitting the linear model itself.

I ran into a to me surprising result on running lm with an orthogonal polynomial among the predictors. The lm command resulted in Error in qr(X) : NA/NaN/Inf in foreign function call (arg 1) Error during wrapup: despite my using a "subset" in the call to get rid of NA's. poly is apparently evaluated before any NA's are subsetted out of the data. Example code (attached to

Dear All: I am having some trouble with date variables when NAs are present. The following example illustrates (see below for output of version): > library(chron) > minor.test <- c( "NA", "NA", "1988-02-08", + "1988-02-08", "NA", "1987-11-23", "1988-09-03", "1991-10-15", +

Dear All -- I am trying to use within a little table producing code an anova comparison of two gls fitted objects, contained in a list of such object, obtained using nlme function gls. The anova procedure fails to locate the second of the objects. The following code, borrowed from the help page of anova.gls, exemplifies: --------------- start example code --------------- library(nlme) ##

I am trying to use tapply to estimate the average wage in a set of Year*Education cells using sampling weights, as well as some other other statistics using the weights). I am having trouble trying to figure out how to pass the weights to the function, using: > tapply(wage,list(Educc,Year),weighted.mean, w=weight) whieh produces warnings of the type: 3: longer object length is not a

I am having trouble using Jim Lindsey's libraries because of unresolved symbols. I am currently using R 0.65.0, but had this problem in earlier releases as well. I have a RedHat 6.0 Linux on i386 and use egcs (upgraded to that distributed with rawhide, after first failures with the libraries): egcs-g77-1.1.2-19 egcs-1.1.2-19 Installation of the libraries works but on loading >

I have fitted a number of models with receipt of social assictance (toim1) during a year (values 0 or 1) with a number of covariates. The data include sampling weights which I use in the models. Using the exact same data, glm() under 1.0.1 and 1.1.0 give different results in many (but not all) of the models. I have re-installed 1.0.1 to check this and I found now mention in the NEWS file that

Hello -- I am plotting multiple densities in a single plot. If the max of a new density (added with 'lines()') is sufficiently larger than that of the one first plotted (using 'plot()'), the new density is cut or trucated off of the figure. Is there a simple way of adjusting the yscale after all lines have been added? Or is the procedure to be used to first estimate all

Is there a weighted median function out there similar to weighted.mean() but for medians? If not, I'll try implement or port it myself. The need for a weighted median came from the following optimization problem: x* = arg_x min (a|x| + sum_{k=1}^n |x - b_k|) where a : is a *positive* real scalar x : is a real scalar n : is an integer b_k: are negative and positive scalars

Dear All, on rbind:ing together a number of data.frames, I found that character variables are converted into factors. Since this occurred for a data identifier, it was a little inconvenient and, to me, unexpected. (The help page explains the general procedure used. I also found that on forming a data frame, character variables are converted to factors. The help page on read.table has the

Dear R-users, I intend to do a spatial analysis on the genetic structuring within a population. For this I had thought to prepare a kernel density estimate map showing the spatial distribution of individuals, while incorporating the genetic distances among individuals. I have a dataset of locations of N unique individuals (XY-coordinates) and an NxN matrix with the genetic distances given as a

There is a bug in the command-line handling of 0.65.0 under Unix that may affect some users of R-inferior-mode under ESS, as that sets --no-readline as the first argument, and any arguments after that are ignored. The fix is simple: delete line 448 of src/unix/sys-common.c (`break;') and re-compile. The most used arguments are (I'm told) --vsize and --nsize. I find it more convenient to

Dear Debian R users, This is more of an apt question rather than R. I have a testing Debian system, but would like to use the unstable packages for R, *without* using the -t flag in apt-get. I think this is done by using a 'pin' rule in /etc/apt/apt.conf, but don't understand how this should be done. Can somebody provide an example please? Cheers, -- Seb

I would like to fit a Pareto Distribution and I am using the following codes. I thought the fitted (fit1) should be the fitted value for the data, is it correct? As the result of the "fitted" turns out to be a single value for all. fit=vglm(ycf1 ~ 1, pareto1(location=alpha), trace=TRUE, crit="c") fitted(fit) The result is fitted(fit) [,1] [1,] 0.07752694

Hi, I'm using the ineq package to calculate some concentration measures (Gini, Herfindal, ...) and I was wondering if there's around also a function to calculate standard error on these measures. If not, is anybody aware of where I can find a reference on this point? Thanks. -- ======================================================== Angelo Secchi PGP Key ID:EA280337