similar to: prcomp

I've been trying to build a bundle with the R-devel snapshot from yesterday. (Yes I know it is unstable and just tell me if I shouldn't be trying to do this yet.) It is failing with the message tar : /dev/rmt/0 : Permission denied It happens after "removing junk files" and just after the message "building dse_2000.9-1.tar.gz" It looks to be coming from the line in

(-2) %% 12 seems to give the wrong result in R pre 63.3: > e1 <- -2 > e2 <- 12 > e1 %% e2 [1] -2 > e1 - floor(e1/e2) * e2 [1] 10 In Splus: > e1 <- -2 > e2 <- 12 > e1 %% e2 [1] 10 > e1 - floor(e1/e2) * e2 [1] 10 Paul Gilbert -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-devel mailing list -- Read

Peter, As I understand your Q. You probably have data that is similar to each other like stock Prices for all RHS variable. In that case the difference between corr and cov is not significant; however, if your RHS contains totally dissimilar variables it matters a great deal. If x1 income, x2 job type, x3 Education level, etc..., then taking cov of these variables would not be desireable

I've been working on a revised version of prcomp and princomp. Below is my current draft of prcomp, which is marginally different from V&R. I've added center and scale as optional arguments. However, scale causes the following: > zi _ prcomp(iris[,,2]) Warning: ignored non function "scale" because scale is both a variable and a function. Is there any way to avoid this

What is the Rd file alias and usage syntax for an S4 assignment method? I have been trying variations on \alias{TSdoc<-,default-method} \usage{ \S4method{TSdoc}{default}(x) <- value but so far I have not got it right according to various codoc, etc, checks. Paul Gilbert ==================================================================================== La version fran?aise

Perhaps this is not a bug but rather my misunderstanding of lty and col. I would like to generate a legend for plots as follows: par(mfcol = c(2, 1), mar = c(5.1, 6.1, 4.1, 2.1)) matplot(t(matrix(1:8,8,20)), type="l") par(mfg = c(2, 1, 2, 1)) box(col = 0) # Rbug workaround. Thanks Martin legend((par()$usr)[1:2], (par()$usr)[3:4], as.character(1:8), lty=1:8, col=1:8,

Perhaps this is not a bug but rather my misunderstanding of lty and col. I would like to generate a legend for plots as follows: par(mfcol = c(2, 1), mar = c(5.1, 6.1, 4.1, 2.1)) matplot(t(matrix(1:8,8,20)), type="l") par(mfg = c(2, 1, 2, 1)) box(col = 0) # Rbug workaround. Thanks Martin legend((par()$usr)[1:2], (par()$usr)[3:4], as.character(1:8), lty=1:8, col=1:8,

kalish at psy.uwa.edu.au wrote: > > I'm a newbie at R, and can't get libraries to really work. > I did this: > > library(help = mva) > cancor Canonical Correlations > cmdscale Classical (Metric) Multidimensional Scaling > dist Distance Matrix Computation > hclust Hierarchical Clustering

I had a couple of problems getting R 0.90.0. In case anyone has similar problems, I though I would mention them. 1/ I can't use "ftp cvs.r-project.org" from either home or work. The ftp service does not seem to be available. Perhaps this is intended. I only discovered it because I thought the file I got through Netscape might be corrupted. (I don't understand why Netscape

There was at one time some discussion about supporting documentation of multiple functions in one Rd file. Is that supported or still in the plans? Paul Gilbert -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the

Some webpage has described prcomp and princomp, but I am still not quite sure what the major difference between them is. Can they be used interchangeably? In help, it says 'princomp' only handles so-called R-mode PCA, that is feature extraction of variables. If a data matrix is supplied (possibly via a formula) it is required that there are at least as many units as

I do not understand, from a PCA point of view, the option center=F of prcomp() According to the help page, the calculation in prcomp() "is done by a singular value decomposition of the (centered and possibly scaled) data matrix, not by using eigen on the covariance matrix" (as it's done by princomp()) . "This is generally the preferred method for numerical accuracy"

Hello, Can you get eigenvalues in addition to eigevectors using prcomp? If so how? I am unable to use princomp due to small sample sizes. Thank you in advance for your help! Rebecca Young -- Rebecca Young Graduate Student Ecology & Evolutionary Biology, Badyaev Lab University of Arizona 1041 E Lowell Tucson, AZ 85721-0088 Office: 425BSW rlyoung at email.arizona.edu (520) 621-4005

Dear all, perhaps I am using princomp.formula and prcomp.formula in a way that is not documented to work, but then the documentation just says: formula: a formula with no response variable. Thus, to avoid a lot of typing, it would be nice if one could use '.' and '-' in the formula, e.g. > library(DAAG) > res <- prcomp(~ . - case - site - Pop - sex, possum)

I seem to remember an error like this being mentioned before, but if it wasn't: > zz <- density(rnorm(100)) > plot(zz) Error in plot.new() : Figure margins too large > version _ platform sparc-sun-solaris2.6 arch sparc os solaris2.6 system sparc, solaris2.6 status major 0 minor 90.1 year 1999 month December day 15 language R Paul Gilbert

I am getting the following: *** Weave Errors *** Error in driver$runcode(drobj, chunk, chunkopts) : Error in eval(expr, envir, enclos) : couldn't find function "pacf.mts" *** Source Errors *** Error in eval(expr, envir, enclos) : couldn't find function "pacf.mts" make[1]: *** [checkVignettes] Error 1 I don't really understand the new namespace mechanism,

Something has changed in the S4 default for coercing. Am I now suppose to use setAs, or is there something else I should do to make this work: R version 2.7.0 (2008-04-22) .... > require("methods") > setClassUnion("OptionalPOSIXct", c("POSIXct", "NULL")) [1] "OptionalPOSIXct" > setClass("TSmetax",

According to R help: princomp() uses eigenvalues of covariance data. prcomp() uses the SVD method. yet when I run the (eg., USArrests) data example and compare with my own "hand-written" versions of PCA I get what looks like the opposite. Example: comparing the variances I see: Using prcomp(USArrests) ------------------------------------- Standard deviations: [1] 83.732400 14.212402

One of the functions I would like to clean out of my syskern package is a program to send mail. This is a common feature other programs (e.g. bug.report) may use so I would like it to be included in R/base. I will volunteer to do this as it looks like a fairly straightforward dissection of bug.report but I have some questions: Has anyone done this already? Is "mail" a good name or

I have a generic function test.equal <- function(obj1, obj2, ...) UseMethod("test.equal") however, the only argument that specific methods use is "fuzz" so I would like to change this to test.equal <- function(obj1, obj2, fuzz=???) UseMethod("test.equal") The problem is that some methods use slightly different default values for fuzz than others. How should