similar to: Tuning the nlm function

It would be really nice if nlm took a set of "..." optional arguments that were passed through to the objective function. This level of hacking is probably slightly beyond me: is there a reason it would be technically difficult/inefficient? (I have a vague memory that it used to work this way either in S-PLUS or in some previous version of R, but I could easily be wrong.) Here's

I am trying to view the source code of the function nlm in the stats package of R 2.4.1. I downloaded the source from CRAN and opened nlm.R, and it calls a .Internal function: .Internal(nlm(function(x) f(x, ...), p, hessian, typsize, fscale, msg, ndigit, gradtol, stepmax, steptol, iterlim)) This is the same thing I saw when entering the function name at the R command

Hi everyone. I have a problem that I have been unable to determine either the best way to proceed and why the methods I'm trying to use sometimes fail. I'm using the pf() function in an optimization function to find a noncentrality parameter that leads to a specific value at a specified quantile. My goal is to have a general function that returns the noncentrality parameter that

Dear R list members, I have a question about the proper use of the typsize and fscale arguments to nlm. I use nlm in my sem package to fit general structural-equation models, which entails maximizing a multinormal likelihood with respect to parameters that represent regression coefficients and covariances of variables. The magnitudes of these parameters can be very different. The

Filed as a bug, as suggested by Brian R., Jonathan. Jonathan Rougier Science Laboratories Department of Mathematical Sciences South Road University of Durham Durham DH1 3LE tel: +44 (0)191 374 2361, fax: +44 (0)191 374 7388 http://www.maths.dur.ac.uk/stats/people/jcr/jcr.html ---------- Forwarded message ---------- Date: Wed, 11 Apr 2001 09:15:26 +0100

Hi all, When upgrading to 2.11.1 recently I noticed different results being produced by my code. After much digging I have finally narrowed it to a call to nlm(). This can be replicated by: FixedRemovals<-1836180125888 AbStageInitial<-2223033830403 Rates<- 0.3102445 nlm(function(rootM,Abund,Loss,OtherM) {(Loss-(rootM/(rootM+OtherM)* (1-exp(-(rootM+OtherM)))*

Dear R users, I am using the nlm function for minimization of the very non-linear function of four parameters. I am running 100 simulations and almost always I get the convergence code =2 (Successive iterates within tolerance. Current iterate is probably solution.) [about 75 times of 100]. Frequently, 3 of 4 relative gradients are close to zero and the fourth is huge but there are also cases

Hi Everyone, I have modified my version of R-1.4.1 to include choleski with pivoting (like in Splus). I thought R-core might consider including this in the next version of R, so I give below the steps required to facilitate this. 1. Copied Linpack routine "dchdc.f" into src/appl 2. Inserted line F77_SUBROUTINE(dchdc) in src/appl/ROUTINES 3. Inserted "dchdc.f" into

Can I suggest that in cov and cor the lines if (is.data.frame(x)) x <- as.matrix(x) if (is.data.frame(y)) y <- as.matrix(y) be replaced by if (is.data.frame(x)) x <- data.matrix(x) # coerce logical and factors if (is.data.frame(y)) y <- data.matrix(y) # likewise This would allow things like > data(iris) > cor(iris) which

Hi everyone, Can I suggest the following modification of outer for R-1.3, in the interests of speed and size of calculation: ******************************************************************* "outer" <- function (X, Y, FUN = "*", ...) { no.nx <- is.null(nx <- dimnames(X <- as.array(X))) dX <- dim(X) no.ny <- is.null(ny <- dimnames(Y <-

Hi everyone, I do a lot of work with large variance matrices, and I like to use "crossprod" for speed and to keep everything symmetric, i.e. I often compute "crossprod(Q %*% t(A))" for "A %*% Sigma %*% t(A)", where "Sigma" decomposes as "t(Q) %*% Q". I notice in the code that "crossprod", current definition > crossprod function (x,

ripley@stats.ox.ac.uk wrote: > > On Tue, 14 May 2002, Dirk Eddelbuettel wrote: > > > With a (late prerelease of) 1.5.0 on Windows, using sprintf on NaN > > yields garbage when the number of decimal is specified while it > > works fine for NA: > > > > > sprintf("%.2f", NA) > > [1] "0.00" > > I get that on Linux too, but

Hi everyone, I've noticed that the methods function is incomplete. The obvious example is if I write a function "$.foo", it is not picked up by methods: > "$.foo" <- function(object, name) get(name, envir=object[[1]]) > "$<-.foo" <- function(object, name, value) {assign(name, value, envir=object[[1]]); object} > happy <-

According to the assign helpfile (0.90.1) the "assign" function is function (x, value, pos = -1, envir = sys.frame(sys.parent()), inherits = FALSE, immediate = TRUE) which is not quite the implementation, which is function (x, value, pos = -1, envir = pos.to.env(pos), inherits = FALSE, immediate = TRUE) This seems to have the following interesting effect. "short.fun"

Hi everyone, Can I suggest an addition to the help page for logical AND and OR, indicating the behaviour of NA (which is currently not mentioned at all). I think something simple like an extra paragraph in Details, eg \code{NA} is a valid logical object. Where a component of \code{x} or \code{y} is \code{NA}, the result will be \code{NA} if the outcome is ambiguous. In other words \code{NA

Hi Everyone, I have a piece of C code that uses R_alloc, and so I set DUP=TRUE in the call using ".C". As I understand it this takes a copy of each object passed to my function. If these objects are large then this could be expensive. My question is, if I rewrote the code to use .Call, would I avoid this duplication by using the objects themselves (they are not modified in the code)

The following gives an immediate segmentation fault, v 0.90.1 "fred" <- function(x) { print(x); Recall(x-1)} fred(0) # segmentation fault at recursion 831 Obviously this recursion is non-terminating, but shouldn't it be caught and reported at some limit? In 0.64.1 we had Error: protect(): stack overflow at recursion 831. Cheers, Jonathan. Jonathan Rougier

Might it be possible to tighten the definition of "is.qr". I noticed that after I mistakenly typed example(lm) # make lm object named lm.D9 qr.Q(lm.D9) which exhausted the heap memory and produced two warning messages. As an object of class "lm" has a "qr" component, "is.qr" failed to detect that "lm.D9" was not a "qr" object. The

Hi everyone, Can I suggest the following cosmetic change to cut.default (R-1.3.1), to adjust the labels in the case that include.lowest = TRUE: arrow:dma0jcr% diff -u cut.R my.cut.R --- cut.R Tue Nov 13 12:28:35 2001 +++ my.cut.R Tue Nov 13 12:35:16 2001 @@ -25,6 +25,11 @@ ch.br[-nb], ",", ch.br[-1], if(right)"]"

Hi everyone, There is no mention in ?new.env (R-1.6.0) of what the effect of setting the hash argument of new.env() actually does. What does it mean in performance terms to say that "the environment will be hashed"? Thanks, Jonathan. -- Jonathan Rougier Science Laboratories Department of Mathematical Sciences South Road University of Durham