similar to: gelman.diag question

Dear friends, Over the past weeks, I have been asking a lot of questions about how to use R in Bayesian analysis. I am brand new to R, but I am very pleased with it. I started with winbugs but I found winbugs to be a limited software, not bad but has several limitations. By contrast, R allows the analyst to tackle any problem with a huge set of tools for any kind of analysis. I love R. In

I have been running a Gibbs Sampler to estimate levels of efficiency in the Louisiana Shrimp Industry. I created a matrix (samp) where I stored the results of each iteration for 86 variables. I run 10,000 iterations. So, the matrix samp is 10,000 x 86. I want to use the gelman-rubin test to check for convergence. To do that, I need at least two chains. If I run second chain with different starting

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]]

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

Dear, I'm trying to run diagnostics on MCMC analysis (fitting a log-linear model to rates data). I'm getting an error message when trying Gelman-Rubin shrink factor plot: >gelman.plot(out) Error in chol.default(W) : the leading minor of order 2 is not positive definite I take it that somewhere, somehow a matrix is singular, but how can that be remedied? My code: library(rjags)

Dear Friends, According to Gelman et al (2003), "...Bayesian P-values are defined as the probability that the replicated data could be more extreme than the observed data, as measured by the test quantity p=pr[T(y_rep,tetha) >= T(y,tetha)|y]..." where p=Bayesian P-value, T=test statistics, y_rep=data from replicated experiment, y=data from original experiment, tetha=the function

I am using -mice- for multiple imputation and would like to use the gelman diagnostic in -coda- to assess the convergence of my imputations. However, gelman.diag requires an mcmc list as input. van Buuren and Groothuis-Oudshoorn (2011) recommend running mice step-by-step to assess convergence (e.g. imp2 <- mice.mids(imp1, maxit = 3, print = FALSE) ) but this creates mids objects. How can I

I was trying to generate random numbers with a gamma distribution. In R the function is: rgamma(n, shape, rate = 1, scale = 1/rate). My question is that if X~gamma(alpha, beta) and I want to generate one random number where do I plug alpha and beta in rgamma? and, what is the meaning and use of rate? Thanks for your attention, Jorge [[alternative HTML version deleted]]

Hi, I am trying to recreate the right graph on page 524 of Gelman's 2006 paper "Prior distributions for variance parameters in hierarchical models" in Bayesian Analysis, 3, 515-533. I am only interested, however, in recreating the portion of the graph for the overlain prior density for the half-Cauchy with scale 25 and not the posterior distribution. However, when I try:

Deal all, as MCMClogit does not allow for the specification of several chains, I have run my model 3 times with different random number seeds and differently dispersed multivariate normal priors. For example: res1 = MCMClogit(y~x,b0=0,B0=0.001,data=mydat, burnin=500, mcmc=5500, seed=1234, thin=5) res2 = MCMClogit(y~x,b0=1,B0=0.01,data=mydat, burnin=500, mcmc=5500, seed=5678, thin=5) res3 =

I decided to update my packages and then had a problem with loading the Matrix package http://cran.at.r-project.org/bin/windows/contrib/2.4/Matrix_0.9975-9.zip This is what happened when I tried to load it in: > library("Matrix") Error in importIntoEnv(impenv, impnames, ns, impvars) : object 'Logic' is not exported by 'namespace:methods' Error:

Is there a quick way to fit student-t regressions (that is, a regression with t-distributed error, ideally with the degrees-of-freedom parameter estimated from the data)? I can do it easily enough in Bugs, or I can program the log-likelihood in R and optimize using optim(), but an R version (if it's already been written by somebody) would be convenient, especially for teaching purposes.

Hi, all. I'm trying to automate some regression operations in R but am confused about how to evaluate expressoins that are expressed as character strings. For example: y <- ifelse (rnorm(10)>0, 1, 0) sex <- rnorm(10) age <- rnorm(10) test <- as.data.frame (cbind (y, sex, age)) # this works fine: glm (y ~ sex + I(age^2), data=test, family=binomial(link="logit"),

I'm trying to figure out how to use lmer to fit models with factors that have some nesting and some non-nested groupings. For example, in this paper: http://www.stat.columbia.edu/~gelman/research/published/parkgelmanbafumi.pdf we have a logistic regression of survey respondents' political preferences (1=Republican, 0=Democrat), regressing on sex, ethnicity, state (51 states within 5

I'm having another problem with lmer(), this time something simpler (I think) involving the coef() function for a model with varying coefficients. Here's the R code. It's a simple model with 2 observations per group and 10 groups: # set up the predictors n.groups <- 10 n.reps <- 2 n <- n.groups*n.reps group.id <- rep (1:n.groups, each=n.reps) # simulate the varying

I have written a function called mcsamp() that is a wrapper that runs mcmcsamp() and automatically monitors convergence and structures the inferences into vectors and arrays as appropriate. But I have run into a very little problem, which is that mcmcsamp() shortens the variable names. For example: > set.seed (1) > group <- rep (1:5,10) > a <- rnorm (5,-3,3) > y <-

I've been trying to keep track with lmer, and now I have a couple of questions with the latest version of Matrix (0.995-4). I fit 2 very similar models, and the results are severely rounded in one case and rounded not at all in the other. > y <- 1:10 > group <- rep (c(1,2), c(5,5)) > M1 <- lmer (y ~ 1 + (1 | group)) > coef(M1) $group (Intercept) 1 3.1 2

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 While I'm not an R expert, I have used R on Windows XP. Now I've moved to Ubuntu (Intrepid), and I'm trying to configure R to work with the Gelman and Hill _Data Analysis Using Regression and Multilevel/Hierarchical Models_. So far, it's not working. I start by following the instructions for installing arm and BRugs at

Hi all. Are there any R functions around that do quick logistic regression with a Gaussian prior distribution on the coefficients? I just want posterior mode, not MCMC. (I'm using it as a step within an iterative imputation algorithm.) This isn't hard to do: each step of a glm iteration simply linearizes the derivative of the log-likelihood, and, at this point, essentially no

I want to write a function to standardize regression predictors, which will require me to do some character-string manipulation to parse the variables in a call to lm() or glm(). For example, consider the call lm (y ~ female + I(age^2) + female:black + (age + education)*female). I want to be able to parse this to pick out the input variables ("female", "age",