similar to: boot statictic fn for dual estimation of 2 stats?

In polr.R the (several) functions gmin and fmin contain the code > theta <- beta[pc + 1L:q] > gamm <- c(-100, cumsum(c(theta[1L], exp(theta[-1L]))), 100) That's bad. There's no reason to suppose beta[pc+1L] is larger than -100 or that the cumulative sum is smaller than 100. For practical datasets those assumptions are frequently violated, causing the

R Users: I am trying to estimate a model of fertility behaviour using birth history data with maximum likelihood. My code works but is extremely slow (because of several for loops and my programming inefficiencies); when I use the genetic algorithm to optimize the likelihood function, it takes several days to complete (on a machine with Intel Core 2 processor [2.66GHz] and 2.99 GB RAM). Computing

Hello, I was trying to build some functions which I would like to integrate over an interval using the function 'integrate' from the 'stats' package. As an example, please consider the function h(u)=sin(pi*u) + sqrt(2)*sin(pi*2*u) + sqrt(3)*sin(pi*3*u) + 2*sin(pi*4*u) Two alternative ways to 'build' this function are as in f and g below: coeff<-sqrt(1:4)

Greetings all, Ran into a strange problem with the krige function from geoR. The problem that I am having is that while the krige function seems to work well, the resulting predicted values are all NAs. Given the size of the datasets I am working with can't attach it, but I can provide snippets of the datasets. > casedata station year month day obs mpe bias type

Hi R-help, I am working with US COOP network station data and the files are concatenated in single rows for all years, but I need to pull these apart into rows for each day. To do this, I need to extract part of each row such as station id, year, mo, and repeat this against other variables in the row (days). My problem is that there are repeated values for each day, and the files are fixed width

Hi, does anyone have a quick answer to the question of how to carry out interval regression in R. I have found "ordered logit" and "ordered probit" as well as multinomial logit etc. The thing is, though, that I want to apply logit/probit to interval-coded data and I know the cell limits which are used to turn the quantitative response into an ordered factor. Hence, it does

Hi all, I've just installed R on my Mac & PC. The base demo run fine.. But I'm encountering several pb with some packages (installed using CRAN binaries using the menu) - Lattice: > demo(lattice,package='lattice') demo(lattice) ---- ~~~~~~~ Type <Return> to start : > require(grid) [1] TRUE > old.prompt <- grid.prompt(TRUE) > old.settings

I am working with a somewhat complicated structure in which I need to deal with a function that takes ``basic'' arguments and also depends on a number of parameters which change depending on circumstances. I thought that a sexy way of dealing with this would be to assign the parameters as objects in the environment of the function in question. The following toy example gives a bit of the

Hello, I am trying to move/copy a virtual user's maildir to another virtual user but am running into problems with dsync and doveadm. I'm trying to move the maildir of a user who is no longer with the company to a manager's maildir. For doveadm I am using the command: doveadm move -u scavenaugh at lamontanita.coop jhenning at lamontanita.coop/INBOX/scavenaugh INBOX ALL

As part of carrying out a complicated maximum likelihood estimation, I am trying to learn to program likelihoods in R. I started with a simple probit model but am unable to get the code to work. Any help or suggestions are most welcome. I give my code below: ************************************ mlogl <- function(mu, y, X) { n <- nrow(X) zeta <- X%*%mu llik <- 0 for (i in 1:n) { if

Dear R users, I have the following codes: zeta <- rep(1,8) n <- 7 for (i in 1:2){ beta <- zeta[1:n+(i-1)*(n+1)] print(beta) parm <- zeta[i*(n+1)] print(parm) } ################### The output is as follows: [1] 1 1 1 1 1 1 1 [1] 1 [1] NA NA NA NA NA NA NA [1] NA ####################### The outcome I want to get is: [1] 1 1 1 1 1 1 1 [1] 1 [1] 1 1 1 1 1 1 1 [1] 1 How could I get the

Please pardon an extremely naive question. I see related earlier posts, but no responses which answer my particular question. In general, I'm very confused about how to do variance decomposition with random and mixed effects. Pointers to good tutorials or texts would be greatly appreciated. To give a specific example, page 193 of V&R, 3d Edition, illustrates using raov assuming pure

Hi, I am new to R and this is probably a very basic question but I can?t seem to figure out a solution. I am creating a stacked ggplot with the following data and code: PercentageData.csv looks like this: decision treatment percentage labtreatment defect 0 53.49 COMMON defect 1 78.00 ASYMMETRIC defect 2 96.67 PRIVATE coop 0 46.51 COMMON coop 1 22.00 ASYMMETRIC coop 2 3.33 PRIVATE %Load data:

Hi, I am working on a package which requires separate documentation (tutorial documentation, really, with a lot of beautifully latexed equations), and does not use R-help. I am trying to make it so that my help function will automatically search R-help if the help topic isn't found in my documentation. The function looks something like this: help.pkg <- function(topic) { #

Hi, I am working on a package which requires separate documentation (tutorial documentation, really, with a lot of beautifully latexed equations), and does not use R-help. I am trying to make it so that my help function will automatically search R-help if the help topic isn't found in my documentation. The function looks something like this: help.pkg <- function(topic) { #

First some data errors I get with both nv20 exa and nv20 dri/mesa. 1. RT_FORMAT LINEAR + X8R8G8B8 Ch 1/5 Class 0x0597 Mthd 0x0208 Data 0x00800080:0x00000105 Ch 1/5 Class 0x0597 Mthd 0x0208 Data 0x01000100:0x00000105 LINEAR + A8R8G8B8 Ch 1/5 Class 0x0597 Mthd 0x0208 Data 0x01000100:0x00000108 Ch 1/5 Class 0x0597 Mthd 0x0208 Data 0x00800080:0x00000108 The only value I found in renouveau dump

Dear all, It appears that MASS::polr() and Design::lrm() return the same point estimates but different st.errs when fitting proportional odds models, grade<-c(4,4,2,4,3,2,3,1,3,3,2,2,3,3,2,4,2,4,5,2,1,4,1,2,5,3,4,2,2,1) score<-c(525,533,545,582,581,576,572,609,559,543,576,525,574,582,574,471,595, 557,557,584,599,517,649,584,463,591,488,563,553,549) library(MASS) library(Design)

install.packages works for Linux because the directory structure is not version dependent, as it is for the Windows download. That should be fixed as soon as my sys admin consents to install R 1.9.0 so we can do the cross compile. Of course, you are right, Martin and Peter, that Zelig should be on CRAN proper. We just need to write a few .Rd files to be compliant with R check, and change our

Hi, Is there a way to make demo() print comments along with the code and output? For example, if I use something like readline("..."), demo prints both readline("...") and ...; as far as I can tell, this is also true of print() and cat(). I just want students to stop and think about every command in my demo scripts. Thanks, Olivia.

Dear all, To modelize the abundance of fish (4 classes) with a set of environmental variables, I used the polr and predict.polr functions. I would like to know how to bring the cumulated probabilities back to a discrete ordinal scale. For the moment I used the predict.polr function with the argument "class". Is there an other way? polrf <- polrf <- polr_mod(formula =