similar to: Mass: lda and collinear variables

Hi all, currently I'm working with physical data stored in a data.frame. I have N observations, typically 100-300 per data set. Each row in a set holds M (typically 2100) variables which represent a curve. For linear discriminant analysis I chose first to do a wavelet transform (because M >> N) and then feed the transformed data (of level L) in lda. This works fine (e.g. error <

hi all, I've got to import CSV-datasets (with variable-names in the first line) into data.frames. each is about 12MB (or more!) with 1823 columns and about 500 rows. the first 22 columns are in "character"-mode, the rest is "numeric". I run R 1.4.1 on a Windows 2000 system. First I tried read.table() which works fine for a low number of cases (say, 40). with all cases

Hi, how can I scale the x- and y-axis of a "plot" to the same scale? My problem: The following command sequence produces the plot in a square. What I want is the x-axis to be 5 times as wide (measured e.g. in pixels) as the y-axis is long (because y ranges from -1 to 1 and x ranges from 0 to 10). x <- seq( from=0, to=10, by=.1) sinx <- sin(x) plot( x, sinx, type="l")

Hi everybody, I'm using Windows XP Prof, R 2.5.1 and a Pentium 4 Processor. Now, I want to solve a quadratic optimization program (Portfolio Selection) with the quadprog package I want to minimize (\omega'%*%\Sigma%*%\omega) Subject to (1) \iota' %*% \omega = 1 (full investment) (2) R'%*%\omega = \mu (predefined expectation value) (3) \omega \ge 0 (no short sales). Where

org.omegahat.R.Java.REvaluator e = new org.omegahat.R.Java.REvaluator(); Object val = e.eval("objects()"); if(val != null) { String[] objects = (String[])val; for(int i = 0 ; i < objects.length; i++) System.err.println("("+i+") " + objects[i]); } hello, thanks to Philippe Grosjean's work I finally got SJava working (on Windows XP!!), so that I can

hello all, for my diploma-thesis i want to statitically analyze near-infrared-spectra. a spectrum is given by the y-values of 1038 equi-distant x-points. in nature, a spectrum is a continuous curve. for analysis, every x-point is seen as a statistical variable. now my problem: first, i read a csv-table in a data.frame called sTable via read.table. besides some meta-data there are 1038 variables

Hi, I have 2 g729 licences - what I want to do is use g729 by default but if I get more than 2 calls at a time, use gsm for the others. So, I put this on all my sip providers: disallow=all allow=g729 allow=gsm However, this just seems to use gsm for everything. If I comment out the gsm line, it then uses g729. I thought it would use the codec's in the order they are allowed - is this

Dear R-help list, apparently lda from the MASS package can be used in situations with collinear variables. It only produces a warning then but at least it defines a classification rule and produces results. However, I can't find on the help page how exactly it does this. I have a suspicion (it may look at the hyperplane containing the class means, using some kind of default/trivial

Dear R-help list, two issues regarding lda. 1) I'm puzzled by the fact that lda's in-build cross-validation gives results different from the manual cross-validation routine that I run (of course mine may be wrong, but I don't think so). See here: library(MASS) set.seed(12345) n <- 50 p <- 10 # or p<- 200 testdata <- matrix(ncol=p,nrow=n) for (i in 1:p) testdata[,i]

Hi there Sorry for what may be a naive or dumb question. I have the following data: > x <- c(1,2,3,4) # predictor vector > y <- c(2,4,6,8) # response vector. Notice that it is an exact, perfect straight line through the origin and slope equal to 2 > error <- c(0.3,0.3,0.3,0.3) # I have (equal) ``errors'', for instance, in the measured responses Of course the

Hi; I emailed monty@xiph.org about this before I noticed the mailing list existed; I suppose it can't ask to hurt here too. We're about to release a product which has support for multiple languages; as a result, the license text and documentation has been translated into each of these languages. As the product includes Ogg Vorbis playback using libvorbis, we've obviously got to

Dear Thomas, Unfortunately, I do not know if any packages implement this functionality. Though, it is a topic that interests me. Unlike the "classic discriminant", I prefer to work with the reduced polynomial. This "discriminant" is generalizable to a superset of Chebysev polynomials (which I called Cardano-polynomials). x^3 - 3*c*x - 2*d = 0 x^5 - 5*c*x^3 + 5*c^2*x - 2*d =

Hallo NG-Leser, ich denke mal, mir fehlt vielleicht einfach nur die Erfahrung, aber ich hab bisher _kein_ einziges Win-Programm unter Linux zum Laufen bekommen. Eigentlich m?chte ich nur einen IE 5.5 benutzen k?nnen, um zu sehen, ob meine unter Linux entwickelten Webpages auch im IE gut aussehen. (jeder Webmaster kennt ja die Probleme) Aber mit Wine ist da wohl nix zu machen, wie? Ist das

Hallo! I have a problem with fitting data with nls. The first example with y1 (data frame df1) shows an error, the second works fine. Is there a possibility to get a fit (e.g. JMP can fit also data I can not manage to fit with R). Sometimes I also got an error singularity with starting parameters. # x-values x<-c(-1,5,8,11,13,15,16,17,18,19,21,22) # y1-values (first data set)

Hi! Does anyone know how to do the test for goodness of fit of a logistic model (in rms package) after running fit.mult.impute? I am using the rms and Hmisc packages to do a multiple imputation followed by a logistic regression model using lrm. Everything works fine until I try to run the test for goodness of fit: residuals(type=c("gof")) One needs to specify y=T and x=T in the fit. But

Here are the functions documented in the Blue Book that I found missing in R (ignoring the ones which are obviously outdated). aggregate allocated amatch axes chull clorder cutree cycle date debugger dget discr faces interp l1fit labclust lag loglin monthplot mstree mulbar napsack odometer persp plclust plotfit rep.int restore rreg sabl sablplot set.seed smooth sort.list Stable stars

On 05/28/15 15:27, Yuanfang Chen wrote: > #define GET_BIT(lll) \ > // blah blah > > #define G(label1,label2) \ > { \ > // decent amount code \ > ... > while (1) { \ > GET_BIT(label2); \ > }; \ > } > > void f() { > if (..)

#define GET_BIT(lll) \ // blah blah #define G(label1,label2) \ { \ // decent amount code \ ... while (1) { \ GET_BIT(label2); \ }; \ } void f() { if (..) G('c', 'd'); while ( .. ) G('a','b'); } After perf sampling, a lot

Hello, All: The vignette with the sos package used "upquote.sty", required for R Journal when it was published in 2009. Current CRAN policy disallows "upquote.sty", and I've so far not found a way to pass "R CMD check" with sos without upquote.sty. I changed sos.Rnw per an email exchange with Prof. Ripley without solving the problem; see below. The

Hi, Is there a way to make windows2000, xp and 2003 work with unencrypted passwords as a domain member in a domain with a Samba Server as PDC? Igor -- "F?r mich sitzen in deutschen Talkshows viel zu viele Leute mit einem Monatseinkommen von 20 000 Euro herum, die denen mit 2000 sagen, sie m?ssten den G?rtel enger schnallen" - Harald Schmidt