similar to: maintainer of strucchange unreachable?

>>>>> "PG" == Philippe Grosjean <phgrosje at ulb.ac.be> writes: PG> I am interested by your list of students wishes, since I am PG> developing a GPL user interface for math/stat calculation PG> engines (among others: R and Splus, but also Octave, Scilab PG> and Mathematica,...). It will run under Windows only (for the PG> moment),

using: identify(...., plot=FALSE) allows identifying points in a graph without printing the corresponding label in the graph. This works fine in R for Windows. However, when I copy the graph as metafile into Word, the corresponding label appears in black font in the copied picture. Obviously, identify() prints the label anyway, in "invisible" font or so, in the graph, and this

Hi, I have 16 tables of 39 variables with around 1500 to 3500 cases in each table. These 16 tables are in 16 different data frames. I want to merge them in a single large data frame, so: All <- rbind(T1, T2, ...) The problem: it is VERY slow, and takes a lot of memory (> 500 Mb) on my Athlon XP1800+, 1.75 Go memory, Win 2000 Pro SP1, R 1.4.1. Any suggestion to improve speed, and/or memory

Hello, I am doing several self-starting growth functions for using with nls(). When I list the self-starting functions included in nls library, for instance, SSlogis, there is: > SSlogis function (input, Asym, xmid, scal) ... <environment: 03476D20> attr(,"class") [1] "selfStart" What is this <environment: 03476D20> instruction? By using deriv() and then

Hi, I have submitted a package to CRAN in ftp://ftp.tuwien.ac.at/incoming/pastecs_1.0.tar.gz. The R extension manual advises to send a mail to cran at ci.tuwien.ac.at about it, but it fails. I have also tried WWWadmin at ci.tuwien.ac.at. Are these email adresses still valid? Best, Philippe Grosjean ...........]<(({?<...............<?}))><............................... ) ) ) )

Generalised Inverse: The Moore-Penrose Generalisied Inverse is probably better defined as a pseudo-Inverse that arises in solving least squares problems. Another well known pseudo-Inverse is the so-called Drazin pseudo-Inverse. If memory serves (and it's been 10-12 years!) it can be obtained via a diagonalisation. Anyway, I dare say Prof. Ripley (among others) probably has "all the

Hello, I would like to plot two superposed surfaces (original data, and smoothed models). Basically, I would like to create a usual persp plot with box, and then superpose a second surface (without box and axes) on the top plane of the box defined by the first graph. I don't know if it is clear :-( Is it possible to draw such a second surface in an existing persp plot in R? Another (related)

Hello all, Since I got no answer to my first mail, I suspect I did not formulate my question adequately, so I try again. In R, one can debug or trace a function 'foo' with debug(foo) or trace(foo), respectively. This leads to a special treatment of the function 'foo' until one enter undebug(foo) or untrace(foo). I would like to know if there is a convenient way to know at any

Hi, Under Windows, I am exporting graphs from R (in metafile -emf- format), and want to combine them using a graphic package. It happens that the background of the graph is represented by a filled rectangle (with the color given by bg=...). This is to be expected. However, I find no options to disable this and produce a graph with transparent background. Does such an option exist? If not, then

Hello everybody, I am making a modified version of "Stephan Steinhaus' benchmark test for number crunching, v. 2, (see http://www.scinetificweb.com/ncrunch/ncrunch.pdf for the original version), comparing several functions of some math/stat software. R is not performing bad at all... except for the sorting of a 1,100,000 random vector (test #3) which is the worst of all (see cell F3 in

Hello everybody, I am making a modified version of "Stephan Steinhaus' benchmark test for number crunching, v. 2, (see http://www.scinetificweb.com/ncrunch/ncrunch.pdf for the original version), comparing several functions of some math/stat software. R is not performing bad at all... except for the sorting of a 1,100,000 random vector (test #3) which is the worst of all (see cell F3 in

Hello, nls library provides 6 self-starting models, among them: SSfp, a four parameters logistic function. Its self-starting procedure involves several steps. One of these steps is: pars <- as.vector(coef(nls(y ~ cbind(1, 1/(1 + exp((xmid - x)/exp(lscal)))), data = xydata, start = list(lscal = 0), algorithm = "plinear"))) which assumes an initial value of lscal equal to 0. If lscal

Thorsten is right. There is a direct formula for computing the Moore-Penrose inverse using the singular value composition of a matrix. This is incorporated in the following: mpinv <- function(A, eps = 1e-13) { s <- svd(A) e <- s$d e[e > eps] <- 1/e[e > eps] return(s$v %*% diag(e) %*% t(s$u)) } Hope it helps. Dietrich

Dear useRs, the strucchange package for testing for structural change has been updated: the current version is 1.2-4. The most significant additions were two functions gefp() and efpFunctional(). gefp() implements a class of generalized M-fluctuation tests for testing for parameter instability or structural change in general parametric models including generalized linear models (GLMs).

Dear useRs, the strucchange package for testing for structural change has been updated: the current version is 1.2-4. The most significant additions were two functions gefp() and efpFunctional(). gefp() implements a class of generalized M-fluctuation tests for testing for parameter instability or structural change in general parametric models including generalized linear models (GLMs).

Hi all, I try to use the hdf5 package. I downloaded the Windows binary version, and it claims it requires hdf5dll.dll library, so I download the whole hdf5 1.4.3 package from NCSA. Unfortunatelly, it crashes R. I suspect it is because the package was probably compiled against version 1.2 of hdf5 (as evoked in the help file?) or any other previous version, so I downloaded the source of the package

There is a new package in the devel-section of CRAN called 'strucchange' providing functions for testing on structural change in linear regression relationships. It features tests/methods from the generalized fluctuation test framework as well as from the F test (Chow test) framework. This includes methods to fit, plot and test fluctuation processes (e.g., CUSUM, MOSUM, recursive/moving

On Fri, 7 Apr 2006 16:09:53 +0200 Brandt, T. (Tobias) wrote: > Hi > > Is there a reason why as.matrix.zoo doesn't set the rownames to the > index like as.data.frame.zoo does? Yes, oversight, I think ;-) Added to the devel-version of zoo. I'll try to get it out to CRAN in the next days. Z > Thanks > > Tobias > > > > library(zoo) > > x.Date

Hello, Im using strucchange package in R software in order to apply Bai and Peron (1998, 2003) structural break tests to a set of n=1671 observations with a constant term (no AR terms). For that purpose I have read several papers, for instance Validating Multiple Structural Change Models An Extended Case Study, in which its aim is to replicate the results from Bai and Perron (2003) in R

To the R development team; I found an unusual behavior in zoo when I upgraded to R 2.11.0 - it abruptly terminated when I performed certain operations on large zoo objects. I sent an e-mail to Achim Zeileis and he said this was a potential bug that I should report to the R development team. The details are given below in the thread below. Basically, I can crash R with this code: library(zoo)