similar to: Fw: MLE

May I ask one statistics related question please? I have one query on MLE itself. It's property says that, for large sample size it is normally distributed [i.e. asymptotically normal]. On the other hand it is Efficient as well. My doubt is, how this two asymptotic properties exist simultaneously? If it is consistent then asymptotically it should collapse to "truth" i.e. for large

So, I've embarked on my threatened modifications to the mle subset of the stats4 package. Most of what I've done so far has *not* been adding the slick formula interface, but rather making it work properly and reasonably robustly with real mle problems -- especially ones involving reasonably complex fixed and default parameter sets. Some of what I've done breaks backward

The concrete problem is that I am refereeing a paper where a confidence interval is presented for the risk ratio and I do not find it credible. I show below my attempts to do this in R. The example is slightly changed from the authors'. I can obtain a confidence interval for the odds ratio from fisher.test of course === fisher.test example === > outcome <- matrix(c(500, 0, 500, 8),

Thanks to those who responded to my inquiry about generalized linear mixed models on R and S-plus. Before I summarize the software, I note that there are several ways of doing statistical inference for generalized linear mixed models: (1)Standard maximum likelihood estimation, computationally intensive due to intractable likelihood function (2) Penalized quasi likelihood or similar

Good Afternoon, I am relatively new to R and have been trying to figure out how to estimate regression coefficients using the MLE method. Some background: I am trying to examine scenarios in which certain estimators might be preferred to others, starting with MLE. I understand that MLE will (should) produce the same results as Ordinary Least Squares if the assumption of normality holds. That

Hi the list, I would need some advice on something that looks like a FAQ: the possibility of providing vectors to optim() function. Here is a stupid and short example summarizing the problem: -------------------------------- example 1 ------------ 8< ---------------------- library(stats4) data <- rnorm(100,0,1) lik1 <- function(m, v, data) { N <- length(data) lik.mean <-

Hello! I would like to get MLE for parameter lambda of Poisson distribution. I can use fitdistr() for this. After looking a bit into the code of this function I can see that value for lambda and its standard error is estimated via estimate <- mean(x) sds <- sqrt(estimate/n) Is this MLE? With my poor math/stat knowledge I thought that MLE for Poisson parameter is (in mixture of LaTeX

hi all does anyone know how one would calculate the covariance matrix of a vector of estimated parameters if we use the method of moments technique? one could use bootstrapping techniques but there should be some asymptotic results that could be used as per MLE estimates. a reference would be much appreciated.

I just ran example(glm) and happened to notice that models based on the Gamma distribution gives a t test, while the Poisson models give a z test. Why? Both are b/s.e., aren't they? I can't find documentation supporting the claim that the distribution is more like t in one case than another, except in the Gaussian case (where it really is t). Aren't all of the others approximations

Hi, There is something I don't get with object of class "mle" returned by a function I wrote. More precisely it's about the behaviour of method "confint" and "profile" applied to these object. I've written a short function (see below) whose arguments are: 1) A univariate sample (arising from a gamma, log-normal or whatever). 2) A character string

Simple-mindedly I tried getting MLE and SE for one-parameter model in the same way as for multi-param models. out<-nlm(fn,p=c(2),hessian=T) But sqrt(diag(solve(out$hessian))) gives the answer 1. The Hessian has only one entry, not really a matrix. diag(x) gives 1 if x is just a single number. Is this what I should be doing to get SE for MLE? sqrt(solve(out$hessian)) Thanks very much for

Simple-mindedly I tried getting MLE and SE for one-parameter model in the same way as for multi-param models. out<-nlm(fn,p=c(2),hessian=T) But sqrt(diag(solve(out$hessian))) gives the answer 1. The Hessian has only one entry, not really a matrix. diag(x) gives 1 if x is just a single number. Is this what I should be doing to get SE for MLE? sqrt(solve(out$hessian)) Thanks very much for

Hi everyone! I am using the mle {stats4} to estimate the parameters of distributions by MLE method. I have a problem with the examples they provided with the mle{stats4} html files. Please check the example and my question below! *Here is the mle html help file * http://stat.ethz.ch/R-manual/R-devel/library/stats4/html/mle.html http://stat.ethz.ch/R-manual/R-devel/library/stats4/html/mle.html

Hi, How can we set the environment for the minuslog function in mle()? The call in this code fails because the "ll" function cannot find the object 'y'. Modifying from the example in ?mle: library(stats4) ll <- function(ymax=15, xhalf=6) { -sum(stats::dpois(y, lambda=ymax/(1+x/xhalf), log=TRUE)) } fit.mle <- function(FUN, x, y) { loglik.fun <- match.fun(FUN)

I learned R & MLE in the last few days. It is great! I wrote up my explorations as http://www.mayin.org/ajayshah/KB/R/mle/mle.html I will be most happy if R gurus will look at this and comment on how it can be improved. I have a few specific questions: * Should one use optim() or should one use stats4::mle()? I felt that mle() wasn't adding much value compared with optim, and

I'm trying to figure out the best way of fitting the same negative log-likelihood function to more than one set of data, using mle() from the stats4 package. Here's what I would have thought would work: -------------- library(stats4) ## simulate values r = rnorm(1000,mean=2) ## very basic neg. log likelihood function mll <- function(mu,logsigma) {

Hi, I am looking for some help regarding the use of the mle function. I am trying to get mle for 3 parameters (theta0, theta1 and theta2) that have been defined in the the log-likelihood equation as theta0=theta[1], theta1=theta[2] and theta2=theta[3]. My R code for mle is: mle(Poisson.lik, start=list(theta=c(20,1,1), method="Nelder-Mead", fixed=list(w=w, t1=t1, t2=t2)) But I keep

R 2.3.0, all packages up to date Linux, SuSE 10.0 Hi I want to calculate AIC or BIC from several results from mle calculation. I found the AIC function, but it does not seem to work with objects of class mle - If I execute the following: ml1 <- mle(...) AIC(ml1) I get the following error messale: Error in logLik(object) : no applicable method for "logLik" Therefore I am using the

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

Hi the list, I am experiencing several issues with profile.mle (and consequently with confint.mle) (stat4 version 2.9.2), and I have to spend a lot of time to find workarounds to what looks like interface bugs. I would be glad to get feedback from experienced users to know if I am really asking too much or if there is room for improvement. * Problem #1 with fixed parameters. I can't