similar to: installing online help (PR#423)

Hi I have some data (v. large amount) with a (0,1) response where I want to minimise the errors in the betas rather than SS or deviance. So can anyone point me to a ridge regression function or equivalent for such a logistic regression case? John -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read

Full_Name: Przemys³aw Matuszewski Version: R-1.1.0 OS: Linux RH 6.2 Submission from: (NULL) (195.117.211.244) I have a problem with the package tseries_0.5-2. The source of tseries_0.5-2 was compiled by command R INSTALL /path/to/package. There was build the tseries library. Now when I try to load the package I get the message: ........................... Type "demo()" for

If .../<pkg>/man/ contains a filename beginning with [, such as [.datetimes, Rdconvlib.pl cannot convert that help file into latex at INSTALL time. [Using --no-latex is a workaround.] The error given is: # R INSTALL ssCatalogues : help >>> Building/Updating help pages for package `ssCatalogues' Formats: text html latex example /^[.datetimes$/: unmatched [] in regexp at

Full_Name: Sheila Bryant Version: 1.1.1 OS: Solaris 2.6 Submission from: (NULL) (134.225.16.2) During the 'make' process I get the following: String found where operator expected at /export/bors/bors-01/sws96srb/R-1.1.1/etc/Rdconvlib.pl line 781, near "("</TABLE>\n"" (Missing operator before "</TABLE>\n"?) Bare word found where operator

Dear All First off, let me just add my thanks to all the people involved in the production of R-1.0.0... Well Done!! I'm getting an error installing R-1.0.0 on RedHat 5.2, perl 5.004_04. It did not occur under Solaris 2.6 with perl 5.004_01. During install of the base package (and akima, bootstrap, etc) it gets to the point of building the help pages and it gives this error:

Thanks a lot for "tseries"! The new (0.1-2) version of the tseries package contains the following in ./README : >> Author(s): A. Trapletti <A.Trapletti@ci.tuwien.ac.at>, >> B. LeBaron ("./src/bdstest.c"), >> K. Krischer, and T. M. Kruel ("./src/muin2ser.f", >> "./misc/mutinfo-1.21b.tar.gz") >>

tseries_0.3-0 at CRAN now contains the following new features: NelPlo Nelson-Plosser Macroeconomic Time Series garch Fit GARCH Models to Time Series get.hist.quote Download Historical Finance Data jarque.bera.test Jarque-Bera Test na.remove NA Handling Routines for Time Series garch contains a GARCH estimation routine together

tseries_0.3-0 at CRAN now contains the following new features: NelPlo Nelson-Plosser Macroeconomic Time Series garch Fit GARCH Models to Time Series get.hist.quote Download Historical Finance Data jarque.bera.test Jarque-Bera Test na.remove NA Handling Routines for Time Series garch contains a GARCH estimation routine together

As the 0.65 release should happen within the next few weeks, now would be a good time for updating/improving our impressive collection of add on packages. Issues to look look into include: * Valid and complete DESCRIPTION, TITLE and INDEX files. * Complete data/00Index files (if applicable). * All examples should be executable to that R CMD check passes. * src/Makefile (if there, most likely

Hi the devel list. I am adapting the package.skeleton to S4 classes and methods I would have been very proud to post a new working function on this list. Unfortunately, I do not manage to solve all the problems. Mainly - sys.source does not compile a file with setClass - dumpMethod does not exists yet In the following code, thise two problems are notified by a line ################# Still

Is this a bug-- ------------------------------------------------------------------------------- <234>% R CMD Rd2dvi base.Rd Converting Rd files to LaTeX ... base.Rd Can't use an undefined value as filehandle reference at /opt/R-2.5.1/lib/R/share/perl/R/Rdconv.pm line 78. ENCS is Creating dvi output from LaTeX ... Saving output to 'base.dvi' ... cp: cannot access

Dear R-Users, are there any ARIMA/GARCH-packages/functions for R? Best regards, M. Fischer -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at

It seems to me the following should work (in fact, it comes from someone's SPlus file). Instead, it reads the first 8 lines and then spits out syntax errors. Using nlines=36 works. Using nmax does not. Intel RH5.2 with R90.0. Debugging shows it must be internal. Jim junk <- scan(file="",list(i=0,r1=0,r2=0,lull="",day=""),n=5*36) 1 3 5 no 1 2 1

Full_Name: Kelly Black Version: 2.0.1 OS: FreeBSD 5.3 on AMD64 Submission from: (NULL) (149.106.32.93) I downloaded R-2.0.1 from the R website, ran configure then make and got an error. I will paste a copy of the output from the makefile below. The problem was when the makefile tried to run the R binary. When I came across the error I reran configure, but this time with the following arguments:

Dear R-core, Thank you for your great effort! I am finalising a bundle that works both in R and Splus. But I faced the following minor problems with R CMD under both UNIX and LINUX. 1. R CMD build denies to work with bundles. It reports * checking `DESCRIPTION' package entry ... ERROR: no package entry in `DESCRIPTION' Surely, there is no one, but there is Contains entry. Next, according

Time Series functions in R ========================== I think a good basic S-like functionality for library(ts) in base R would include ts class, tsp, is.ts, as.ts plot methods start end window frequency cycle deltat lag diff aggregate filter spectrum, spec.pgram, spec.taper, cumulative periodogram, spec.ar? ar -- at least univariate by Yule-Walker arima -- sim, filter, mle, diag, forecast

Full_Name: michael klinglemsith Version: R-1.7.1 OS: linux Submission from: (NULL) (134.134.136.4) I run: (note: ] is my unix prompt) ]./configure It seems to work, here are the messages I get from the end of configure: R is now configured for i686-pc-linux-gnu Source directory: . Installation directory: /usr/local C compiler: gcc -D__NO_MATH_INLINES

There seems to be a problem with plot.ts (R Version 0.64.2) >x<-cbind(1:10,2:11) >x<-as.ts(x) >plot(x) Error: subscript (20) out of bounds, should be at most 10 > The problem is located in "[.ts": > x<-cbind(1:10,2:11) > x[is.finite(x)] [1] 1 2 3 4 5 6 7 8 9 10 2 3 4 5 6 7 8 9 10 11 > x<-as.ts(x) > x[is.finite(x)] Error: subscript

With 0.64.1 on Intel RH5.2, abc <- list() abc$abc$abc <- matrix(1:20) mt <- terms(~(abc$abc$abc[,1]==64)|(abc$abc$abc[,1]==65)|(abc$abc$abc[,1]==75) |(abc$abc$abc[,1]==84)|(abc$abc$abc[,1]==85)) model.matrix(mt,model.frame(mt)) crashes. With ab$ab$ab, it does not. Apparently, the bug I reported for 0.64.0 has just been pushed back one step. Jim

Well here is my (first) segmentation fault for this version (R0.90.0) on Intel RH5.2: x <- matrix(0,nrow=1,ncol=3) y <- c(0.1,10,0.01) rbind(x,y) Jim -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the