similar to: Some loglog density plot

Dear all, Me and the Garbage Collector doesn't understand each other... I'm on R-1.0.1 (I have requested an upgrade to the right local people), an osf1 system with an alphaev6 CPU. I have fair amounts of memory to use, but it seems to be used up pretty fast nevertheless. I'm now trying to see what the garbage collector does, I have inserted a gc(v=T) call at a spot in my code. I

Dear all, Either I'm being totally blind now (as you know, the eyes are the first thing that is blinded :-)), or something is missing in "An Introduction to R". The section heading of section 5.7.1 is "Multiplication, inversion and solving linear equations", and since I was looking for the canonical way of inverting a matrix, this was the place to look. However, I found

Dear all, I'm a bit confused about the output from functions that generates random values, e.g. rpois. I'm using 0.65.1 on Digital UNIX alphaev6. If I say > rpois(10,5) output is not unexpectedly: [1] 4 6 5 7 6 5 2 2 5 3 but I figured that if I go: > rpois(10,1:10) I would get a 10x10 matrix as output, with random values for each of the vector elements in the row vectors, but

On 8 Nov 2000, Peter Dalgaard BSA wrote: >Done... Great! >(This kind of behaviour has been observed on various platforms and >various compilers, sometimes getting stuck around 15.15 and sometimes >around 14.5. Others report no problems. Very strange. I've seen one >case where it apparently shifted from one regime to the other.) Yes, it does that here too.... The following is

Dear all, I have an image that I need to filter, and so I'm looking for a method to convolve it with a matrix. If I understood the docs for convolve correctly, it only works in 1D (and I have tried to convolve, it didn't look good). So, I wondered if anybody have implemented 2D convolution in R, or have any good advices to share (beyond having a look at mvfft), before I go hacking?

Dear all, I'm a bit concerned about underflow problems. Such problems typically occur when two almost equal numbers are subtracted. I was wondering if R has any mechanisms for warning users about potential problems, or if any policy has been developed? To check, I just did: > 1.0000000000000001 - 1 [1] 0 > 1.000000000000001 - 1 [1] 1.110223e-15 > 1.00000000000001 - 1 [1]

Dear all, I have been away for a month, but some time ago, I noted something that was very surprising to me. I think this example illustrates it well: > test <- data.frame(col1 = c(1,2), col2=c(3, 4)) > test col1 col2 1 1 3 2 2 4 > apply(test, 1, function(x) browser()) Called from: FUN(newX[, i], ...) Browse[1]> x$col1 NULL Browse[1]> x[["col1"]] [1] 1

Dear all, I am just wondering if anybody has implemented a function that can give a piecewise linear interpolation in more than 2 dimensions? I have looked at the akima package, but I would rather like a piecewise linear interpolation rather than a spline and while it did the job quite satisfactory for 2 dimensions, I need to interpolate in at least three dimensions. If anybody has implemented

I am trying to figure out how to apply a loglog link to a binomial model (dichotomous response variable with far more zeros than ones). I am aware that there are several relevant posts on this list, but I am afraid I need a little more help. The two suggested approaches seem to be: 1) modify the make.link function in GLM, or 2) use the loglog or cloglog functions in the VGAM package.

Dear all, After looking at several packages I decided I would use R for my thesis work (we've even got a site license for S-plus), so I'm learning. I have run into a problem, and nobody on the house has a solution, so I'm wondering if anybody out there can help. I've got two functions of four variables, one outputs a scalar, the other an array, and I want to be able to give an

Hello! I have two matrices of equal dimension ll and lu that I want to do a ks.test on corresponding rows in these matrices (dim(ll) is [1] 101 100). If I do e.g. > ks.test(ll[50,],lu[50,]) just for testing, it displays a lot of numbers, and some more info: [116] -3.000000e-02 -4.000000e-02 -4.000000e-02 -3.000000e-02 -4.000000e-02 [121] -3.000000e-02 -4.000000e-02 -3.000000e-02 -2.000000e-02

Dear all, I'm making a system to create a star-chart, and I have encountered one of the intuitive and clearly thoughtful conventions that are so common in astronomy :-J... Well, the point being, I have to reverse the x-axis. I figured, I might just set xlim=rev(range(x)). Do e.g. > x <- 0:5 > y <- (0:5)^3 > plot(x, y) > plot(x, y, xlim=rev(range(x))) The problem is that here

Dear all, I started a large run this afternoon, and when I came back after dinner, three of five processes had stopped with the error message: Error in matrix(nullprofile, length(nullprofile), nprofiles) : Unimplemented feature in copyVector I have seen anything about this anywhere (and I don't know where to look...). As you might guess, I'm trying to make a matrix where the

Dear all, Uwe e-mailed me yesterday about the problems some time ago. I had hoped someone would have a look at our computers, but due to some unfortunate circumstances, it hasn't happened. However, it seems unlikely that it is connected to a specific piece of hardware. It could be an architecture-dependent problem though. I also had a word with those who did the installation of R, and they

Dear all, There has been some time since I asked about interpolation in higher (>2) dimensions, and I must admit I failed to write a function to do this myself the last time, but eventually ended up doing it in MATLAB. I tried to translate the MATLAB code, but MATLAB code is so much more opaque than R (S) code, so I failed that too, mainly because I could only get one MATLAB session, I would

Dear all, I''m working with the geometric distribution for the time being, and I''m confused. This may have more to do with statistics than R itself, but since I''m getting results from R I find counterintuitive (well, yeah, my statistical intuition has not been properly sharpened), I feel like asking. The point first: If I do > rgeom(1,prob=1) I get: [1] NaN Warning

Dear all, I'm generally not a big fan of GUIs, but I have just discovered one thing where a GUI would be a nice thing: creating color palettes. I'm creating an "image", for transparencies for a lecture I'm giving, so this is going to look great... :-) What I'm out for, is to make green tones and red tones, and a relatively sharp break between them. This break will

Dear all, I have a few files with binary data written by a C program a friend wrote. I allready have program to read these files, Thomas Lumley and Prof Brian D Ripley was kind enough to respond to a question to this list earlier with some code that works perfectly, so this is really no problem, it is more out curiousity. Most of my files consists of 40000 single precision floats, and I figured

I would like to do an R glm() with family = binomial(link="loglog") Right now, the cloglog link exists, which is nice when the data have a heavy tail to the left. I have the opposite case and the loglog link is what I need. Can someone suggest how to add the loglog link onto glm()? It would be lovely to have it there by default, and it certainly makes sense to have the two opposite

Dear all, I've been struggling for days now with a piece of code that I have posted here before, that has a really obscure bug. I think I may have isolated it, but I have no idea what it is.... It might also be a bug in R I guess, as it seems that one or several of list elements are not passed when a function is called, but quite rarely. I have been hacking rather wildly on the histogram