similar to: R computing speed

Hello, I have a R code for doing convolution of two functions: convolveSlow <- function(x, y) { nx <- length(x); ny <- length(y) xy <- numeric(nx + ny - 1) for(i in seq(length = nx)) { xi <- x[[i]] for(j in seq(length = ny)) { ij <- i+j-1 xy[[ij]] <- xy[[ij]] + xi * y[[j]] } } xy } How do I reduce the 2

Hi, I'm trying to find the maximum (likelihood) of a function. Therefore, I'm trying to minimize the negative likelihood function: # params: vector containing values of mu and sigma # params[1] - mu, params[2]- sigma # dat: matrix of data pairs y_i and s_i # dat[,1] - column of y_i , dat[,2] column of s_i negll <- function(params,dat,constant=0) { for(i in 1:length(dat[,1])) {

Dear R-Users, I am trying to use mle() to optimize two (or more) parameters, but I want to specify those parmeters in a data frame rather than having to spell them out separately in the "start" variable of mle(). My call is > mle(negll, start=list(aps=init), fixed=list(measphot=newphot, formod=formod, Nbands=Nbands), method="BFGS") where negll is a function I have

This message is about a curious difference in timing between two ways of computing the same function. One uses expm, so is expected to be a bit slower, but "a bit" turned out to be a factor of >1000. The code is below. We would be grateful if anyone can point out any egregious bad practice in our code, or enlighten us on why one approach is so much slower than the other. The problem

Hello List! I asked this before (with no solution), but maybe this time... I'm trying to project a surface to the XY under a 3d cloud using lattice. I can project contour lines following the code for fig 13.7 in Deepayan Sarkar's "Lattice, Multivariate Data Visualization with R", but it fails when I try to "color them in" using panel.levelplot. ?utilities.3d says there

Dear helpers, I am using the function "constrOptim" to estimate a model with ML with an inequality constraint using the option method='Nelder-Mead'. When I specify the option: hessian = TRUE I obtain the response: Error in f(theta, ...) : unused argument(s) (hessian = TRUE) I guess the function "constrOptim" does not allow this argument which, on the other hand, is

Dear helpers, I wrote a code which estimates a multi-equation model with generalized least squares (GLS). I can use GLS because I know the covariance matrix of the residuals a priori. However, it is a bit slow and I wonder if anybody would be able to point out a way to make it faster (it is part of a bigger code and needs to run several times). Any suggestion would be greatly appreciated. Carlo

Given a vector : pvec=(p1,p2,.... p J) with sum(pvec)=1, all the elements are non-negative, that is, they are probabilities a matrix A ( N* J ), with the elements alpha(ij) are 0 or 1 I want to MAXIMIZE THE RESULT RESULT= product( i=1, to N [ sum ( alpha(ij)* pj , j =1,to J ) ] ) thus, I need to get pvec. how should I do ? for example

Dear all, I am writing an R code to fit a Bayesian mixed logit (BML) via MCMC / MH algorithms following Train (2009, ch. 12). Unfortunately, after many draws the covariance matrix of the correlated random parameters tend to become a matrix with almost perfect correlation, so I think there is a bug in the code I wrote but I do not seem to be able to find it.. dull I know. Has anybody written a

Hello dear R-devel list members. Following an old (2002) thread from R-help (and having myself needing to solve the same question): https://stat.ethz.ch/pipermail/r-help/2002-October/026249.html I patched the {base} function "merge.data.frame" to have it work with a new parameter called "keep_order", and I hope you might consider including this patch (or some variation of it)

With the exception of "L-BFGS-B", all of the other optim() methods return the value of the function when they are given a trivial function (i.e., one with no variable arguments) to optimize. I don't think this is a "bug" in L-BFGS-B (more like a response to an undefined condition), but it leads to a bug in stats4::mle -- a spurious error saying that a better fit has been

I'm using R 2.8.1 on Ubuntu 8.10. I'm writing partly to ask what's wrong, partly to tell other users who search that there is a work around. The General Social Survey is a long standing series of surveys provided by NORC (National Opinion Research Center). I have downloaded some years of the survey data in SPSS format (here's the site:

Hey I'm not really sure what I should put on here, but I am having trouble with my R code. I am trying to get the p-values, R^2s etc for a number of different groups of variables that are all in one dataset. This is the code: #Stand counter st<-1 #Collections stands<-numeric(67) slopes<-numeric(67) intercepts<-numeric(67) mses<-numeric(67) rsquares<-numeric(67)

Hi, I am trying to fit a Johnson SB distribution using fitdist function in fitdistrplus Library. I have defined the Johnson SB distribution from ( http://www.ntrand.com/johnson-sb-distribution/) . But it gives me the follwing errors. Any help would be appreciated #xi = xi #lambda =l #delta =d #gamma = g djohn = function(x,xi,l,d,g) (d/(l*sqrt(2*pi)*((x-xi)/l)*(1-((x-xi)/l))))*exp[-0.5*(g +

Dear R-help readers, I am writing to you in order to ask you a few questions about distribution fitting in R. I am trying to find out whether the set of event interarrival times that I am currently analyzing is distributed with a Gamma or General Pareto distribution. The event arrival granularity is in minutes and interarrival times are in seconds, so the values I have are 0, 60, 120, 180, and

Hi, FWIW: /* Taken from R/src/main/unique.c */ static int requal(SEXP x, int i, SEXP y, int j) { if (i < 0 || j < 0) return 0; if (!ISNAN(REAL(x)[i]) && !ISNAN(REAL(y)[j])) return (REAL(x)[i] == REAL(y)[j]); else if (R_IsNA(REAL(x)[i]) && R_IsNA(REAL(y)[j])) return 1; else if (R_IsNaN(REAL(x)[i]) && R_IsNaN(REAL(y)[j])) return 1;

I am assuming the variable out is the output parameter. However, I don't understand what is out[1+xi*xx>0]? Can someone explain this to me? Thanks in advance, Chen dGEV <- function(x, xi, mu = 0, sigma = 1, logvalue=FALSE) { xx <- (x-mu)/sigma #use the new dGumbel which passes mu and sigma: #if (xi==0) out <- dGumbel(xx,logvalue=TRUE)-log(sigma) if (xi==0) {

Hi thanks for the reply i am really grateful if you can tell me how to make FreeNX work like charm. I am really stuck with it, and after reinstalling the server is definitely pissing off my boss. Please help me thanks. =========================== Please let me review how my FreeNX was screwed up. After i fresh install my CentOS 5, I 'yum install freenx' and so if i am not wrong I

Hello Eik: Thanks. I do not need to sample. Essentially, I have a do loop which produces 24 vectors of length of some length (say k=300) and 24 matrices of 300x300. Then, I simply need to? take the averages of these 24 vectors and matrices: x=(x1+x2+...+x24)/k y=(y1+y2+...+y24)/k I am just looking for ways to do this in a do loop, which requires initialization (to 0's) of x and y. My

Dear All, I am starting to use the tikzDevice package, but I am experiencing some (minor problems). If I try to run the script at the end of the email, I get the following error Error in tools::texi2dvi("normal.tex", pdf = T) : Running 'texi2dvi' on 'normal.tex' failed. Messages: sh: /usr/bin/texi2dvi: not found How do I install the missing texi2dvi? I found some