similar to: Gelman 2006 half-Cauchy distribution

Hello all... I am just starting to teach myself Bayesian methods, and am interested in learning how to use UMacs. I've read the documentation, but the single example is a bit over my head at the level I am at right now. I was wondering if anyone has any simple examples they'd like to share. I've successfully done a couple of simple gibbs examples, but have had a hard time

Hello, I'm taking samples from certain distributions and drawing a density distribution over the histogram of the samples It works fine for the chi-square and for the normal, but not for the cauchy. Any idea what I'm doing wrong? Thanks x <- rchisq(10000, df = 4) hist(x, freq = FALSE, breaks=100) curve(dchisq(x, df = 4), col = 2, add = TRUE) x <- rnorm(10000) hist(x, freq =

I have question (curiosity) regarding returned values of R's qcauchy () function, for nonexceedance probability (F). It seems the ideal returned range of cauchy distribution should be [-Inf,Inf]. For F=0 > qcauchy(0) [1] -Inf but for F=1 > qcauchy(1) [1] 8.16562e+15 It seems to me that the proper return value should be Inf??? For default (location=0,scale=1) quantile function of

Hi I'm using R(2.9.0) and gstat package under Windows to plot sample variograms. When I want to fit them, I don't have the possibility to choose Cauchy functions. Under Mathematica for example, we have it and it seems to be the best one to fit the variograms I have I tested the others functions, they can fit but I would,if possible, use the Cauchy one. If anybody knows something about

Hi all, I am using the function COV.WT to estimate the estimators (location and scale) of a bivariate cauchy distribution. My doubt is about the option WT (weight), cause at the R-help shows that the weight is uniform according to the number of observations. But, checking the theory, for example, the mean is given by mean_estimator=mean(u(s)x)/mean(u(s)), where x=my data (bivariate)

Folks, I wonder if anything could be said about the distribution of a random variate x, where x = N(0,1)/N(0,1) Obviously x is pathological because it could be 0/0. If we exclude this point, so the set is {x/(0/0)}, does x have a well defined distribution? or does it exist a distribution that approximates x. (The case could be generalized of course to N(mu1, sigma1)/N(mu2, sigma2) and one

Full_Name: Jörg Polzehl Version: 1.5.1 OS: Windows 2000 Submission from: (NULL) (193.175.148.198) When calculating MLE's in a variance component model using constrained optimization, i.e. optim(...,method="L-BFGS-B",...) I observed an inproper behaviour in cases where the likelihood function was evalueted at the constraint. Parameters and value of the function at the constraint

Hi, A question. When I run gelman.diag and gelman.plot with mcmc lists obtained from MCMCregress, the results are following. > post.R <- MCMCregress(Size~Age+Status, data = data, burnin = 5000, mcmc = 100000, + thin = 10, verbose = FALSE, beta.start = NA, sigma2.start = NA, + b0 = 0, B0 = 0, nu = 0.001, delta = 0.001) > post1.R <- MCMCregress(Size~Age+Status, data

There are some interesting comments re Paul Murrell's new book, R, & SAS on Andrew Gelman's blog: http://www.stat.columbia.edu/~cook/movabletype/archives/2005/04/a_new_book_on_r.html -- Tony Plate

What is the current state of the R-art for ordered probit models, and more esoterically is there any available R strategy for ordered cauchit models, i.e. ordered multinomial alternatives with a cauchy link function. MCMC is an option, obviously, but for a univariate latent variable model this seems to be overkill... standard mle methods should be preferable. (??) Googling reveals that spss

Dear all, I am trying to use the logistic regression with MCMClogit (package: MCMCpack/Coda) and I want to put a beta prior on the parameters, but it's giving me error message (please see output below) no matter what shape 1 or 2 I use. It works perfect with the cauchy or normal priors. Do you know if there is a catch there somewhere? Thanks logpriorfun <- function(beta,shape1,shape2){

I am attempting to run a Poisson EWMA model using Patrick Brandt's source code. I get the following error when I run the code: Error in dimnames(x) <- dn : length of 'dimnames' [1] not equal to array extent Dimnames(x) looks like this: [[1]] NULL [[2]] [1] "mip" "div" "nom" "unity" "mood"

Dear friends, I run the Gelman-Rubin Convergence test for a MCMC object I have and I got the following result Multivariate psrf 1.07+0i, What does this mean? I guess (if I am not mistaken) that I should get a psrf close to 1.00 but what is 1.07+0i? Is that convergence or something else? Jorge [[alternative HTML version deleted]]

I have a data frame in long format and I would like to randomly divide this data frame in half. The data frame consists of 39622 rows and I initially tried ... randomsample1 <- data[sample(nrow(data),19811), ] Where allows me to randomly select half of the rows and assign them to randomsample1 but then I couldn't figure out how to select those rows that were not selected and assign

I found this a few months ago, but for the life of me I can't remember what the function or package was, and I have had no luck finding it this week. I have found, again, the functions for working with distributions like Cauchy, F, normal, &c., and ks.test, but I have not found the functions for estimating the distribution parameters given a vector of values. What I need to do is

Hi, I noticed this problem on my home desktop running FC4 and again on my laptop running FC5. Both have previously compiled and passed make check-all on 2.3.1 svn revisions from 10 days ago or so. On both these machines, make check-all is consistently failing (4 out of 4 attempts on the FC 4 desktop and 3 out of 3 on the FC 5 laptop) in the p-r-random-tests tests. This is with both default

Dear R users, I followed the instuctions on Dr. Gelman's web to install all of documents that bugs.R needs, but when I try to run the school example that the web posted in R, I got an error: couldn't find function "bugs", what's wrong? Thanks, Jia

Full_Name: Madeleine Yeh Version: 1.9.1 OS: AIX 5.2 Submission from: (NULL) (151.121.225.1) After compiling R-1.9.1 on AIX 5.2 using the IBM cc compiler, I ran the checks. One of them failed. Here is the output from running the check solo. root@svweb:/fsapps/test/build/R/1.9.1/R-1.9.1/tests/Examples: ># ../../bin/R --vanilla < stats-Ex.R R : Copyright 2004, The R

Hi R lovers! I'd like to know how to use the parameter 'start' in the function fitdistr() obviously I have to provide the initial value of the parameter to optimize except in the case of a certain set of given distribution Indeed according to the help file for fitdistr " For the following named distributions, reasonable starting values will be computed if `start'

Hi R-users, Recently, I use maxNR function to find maximizer. I have error appears as follows Error in maxNRCompute(fn = fn, grad = grad, hess = hess, start = start, : NA in the initial gradient My code is mu=2 s=1 n=300 library(maxLik) set.seed(1004) x<-rcauchy(n,mu,s) loglik<-function(mu) { log(prod(dcauchy(x,mu,s))) } maxNR(loglik,start=median(x))$estimate Does anyone know how