similar to: Help on simple problem with optim

Dear List, I am not sure how should i optimize a log-likelihood numerically: Here is a Text book example from Statistical Inference by George Casella, 2nd Edition Casella and Berger, Roger L. Berger (2002, pp. 355, ex. 7.4 # 7.2.b): data = x = c(20.0, 23.9, 20.9, 23.8, 25.0, 24.0, 21.7, 23.8, 22.8, 23.1, 23.1, 23.5, 23.0, 23.0) n <- length(x) # likelihood from a 2 parameter Gamma(alpha,

Thanks to Gabor for setting me right. My code is as follows. I found it useful for learning optim(), and you might find it similarly useful. I will be most grateful if you can guide me on how to do this better. Should one be using optim() or stats4::mle? set.seed(101) # For replicability # Setup problem X <- cbind(1, runif(100)) theta.true <- c(2,3,1) y <- X

Hi List, I would like to plot multiple curves (parametric density curves) in one plot. For example: # parameters for three normal density curves parms = data.frame(ID=c(1,2,3),mu=c(50,55,60),sigma=c(10,12,15)) # I can easily draw three normal density curves using curve(): curve(dnorm(x,mean=parms$mu[1],sd=parms$sigma[1]),from=0, to=150, ylab="density", col="red")

Hi R users, I have a couple of questions about some problems that I am facing with regard to numerical integration and optimization of likelihood functions. Let me provide a little background information: I am trying to do maximum likelihood estimation of an econometric model that I have developed recently. I estimate the parameters of the model using the monthly US unemployment rate series

Dear all, I'm trying to use the "optim" function to replicate the results from the "glm" using an example from the help page of "glm", but I could not get the "optim" function to work. Would you please point out where I did wrong? Thanks a lot. The following is the code: # Step 1: fit the glm clotting <- data.frame( u =

Hello, First time poster here so let me know if you need any more information. I am trying to run an ordered probit with maximum likelihood model in R with a very simple model (model <- econ3 ~ partyid). Everything looks ok until i try to run the optim() command and that's when I get " Error in rep(1, nrow(x)) : invalid 'times' argument". I had to adapt the code from a 4

Sorry about the subject --- On Thu, 24/9/09, KABELI MEFANE <kabelimefane@yahoo.co.uk> wrote: From: KABELI MEFANE <kabelimefane@yahoo.co.uk> Subject: Re: [R] Multiply Normal Curves To: R-help@r-project.org Date: Thursday, 24 September, 2009, 11:48 AM R -helpers   i have been trying to do this problem without must success,i managed to do a graph for x, but it is not what i want to

Hi, I??m trying to use the Win2BUGS package from R and I have a similar problem that reurns with the message: Error in FUN(X[[1]], ...) : symbol print-name too long But, there is no stray ` character in the file ( Sugestions given by: Duncan Temple Lang <duncan> Date: Mon, 26 Sep 2005 07:31:08 -0700 ) The progam in R is: library(R2WinBUGS) library(rbugs) dat <-

Hello, I am trying to plot confidence bands on the mean and prediction bands for the following nonlinear regression, using maximum likelihood via optim. A toy example with data and code of what I am trying to accomplish is: VOL<-c(0.01591475, 1.19147935 ,6.34102460, 53.68809287, 91.90143074, 116.21397007, 146.41843056, 215.64535337, 256.53149673, 315.73609232) Age <-c(1.622222, 2.833333

I feel like a complete dolt, as I know this question has been asked by others on a fairly regular basis, but I'm going in circles trying to get the following to work: id.prob<-function (tt) { library(mvtnorm) #============================ Makeham<-function(tt) { a2=0.030386513 a3=0.006688287 b3=0.039047537 t<-tt-20 h.t<-a2+a3*exp(b3*t) S.t<-exp(-a2*t+a3/b3*(1-exp(b3*t)))

I wrote this: # Setup problem x <- runif(100) y <- 2 + 3*x + rnorm(100) X <- cbind(1, x) # True OLS -- lm(y ~ x) # OLS likelihood function -- ols.lf <- function(theta, K, y, X) { beta <- theta[1:K] sigma <- exp(theta[K+1]) e <- (y - X%*%beta)/sigma logl <- sum(log(dnorm(e))) return(logl) } optim(c(2,3,0), ols.lf, gr=NULL, method="BFGS",

Hi all, I was trying to fit a Gamma hierarchical model using "glmer", but got weird error message that I could not understand. On the other hand, a similar call to the glmmPQL leads to results that are close to what I expect. I also tried to change tha "nAGQ" argument in "glmer", but it did not solve the problem. The model I was fitting has a simple structure - one

Dear all, I had trouble in setting up WinBUGS on my Mac, and I'm seeking for some help here. I followed the instruction by Tom Palmer here: http://www.ruudwetzels.com/MacBUGS/winbugsonmacosx.pdf I installed Darwine 1.1.21, and downloaded WinBUGS14. However, when I double-clicked the WinBUGS14.exe file, a black-box dialog window poped up, and I got error message in the Wine log as

Dear all, I want to min "integrate( (p1*dnorm+p2*dnorm+p3*dnorm)^(1.3))" for p, mu, and sigma. So, I have to estimate 8 parameters(p3=1-p1-p2). I got this warning-"Error in integrate(numint, lower = -Inf, upper = Inf) : non-finite function value." My questions are How could I fix it? I tried to divide into several intervals and sum up, but I got same message. My code is

Are there any functions in R for fitting distributions? In particular, I would like to fit the weibull and extreme-value distributions when: i) the data are given and the maximum likelihood estimates are required; ii) the sample moments are available but the complete data record is not (so moment estimates are required). Any suggestions will be gratefully received.

Hi: I am using R 1.7.0 on Windows. I am having trouble getting "outer" to work on one of my functions. Here is a simple example illustrating my problem: > b1 <- c(1.2,2.3) > b2 <- c(0.5,0.6) > x <- c(3e+01, 1e+02, 3e+02, 5e+02, 1e+03, 1e+04, 1e+05, 1e+06) > y <- c(2,4,2,5,2,3,1,1) > n <- c(5,8,3,6,2,3,1,1) > outer(b1,b2,FUN=bpllkd,x,y,n)

Can someone help me understand the following: > D(expression(dnorm(x, mean)), "mean") [1] 0 > sessionInfo() R version 2.2.1, 2005-12-20, i386-pc-mingw32 attached base packages: [1] "methods" "stats" "graphics" "grDevices" "utils" "datasets" [7] "base" By my computations, this should be

Hi, Apropos of a recent Inf question, I've previously wondered if dnorm "does the right thing" with dnorm(0, 0, -Inf) which gives zero. Should that be zero or NaN (or NA)? The help says "'sd < 0' is an error and returns 'NaN'" and since -Inf < 0 is TRUE, then... is this a bug? Thank you, Stephen Rochester, MN USA

Yes, that looks like a bug and an easily fixable one too. However, I spy another issue: Why do we check the !R_FINITE(x) && mu == x before checking for sd < 0 ? The difference is whether we return ML_NAN; or ML_ERR_return_NAN; but surely negative sd should always be an error? I'd be inclined to do if (sigma < 0) ML_ERR_return_NAN; if(!R_FINITE(sigma)) return R_D__0;

Hi all, Is there any other packages to do numerical integration other than the default 'integrate'? Basically, I am integrating: integrate(function(x) dnorm(x,mu,sigma)/(1+exp(-x)),-Inf,Inf)$value The integration is ok provided sigma is >0. However, when mu=-1.645074 and sigma=17535.26 It stopped working. On the other hand, Maple gives me a value of 0.5005299403. It is an