search for: metrop

I have hit a problem with the design of the mcmc package I can't figure out, possibly because I don't really understand the R function call mechanism. The function metrop in the mcmc package has a ... argument that it passes to one or two user-supplied functions, which are other arguments to metrop. When the two functions don't have the same arguments, this doesn't work. Here's an example. library(mcmc) library(MASS) set.seed(42) n <- 100 rh...

Hi I am using metrop in MCMC library.  Since some times the prior density is 0 and the log prior density would be –Inf, I ask the return value for loglikelihood equal to Min.log, which is defined as log(.Machine$double.xmin)-400, whenever a –Inf occurs to the logdensity.  However, I noticed if two Min.log’s happen in a...

The functions metrop and temper in the mcmc package have a debug = FALSE argument that when TRUE adds a lot of debugging information to the returned list. This is absolutely necessary to test the functions, because one generally knows nothing about the simulated distribution except what what one learns from MCMC sampl...

...unction to find g1,x1,sigma2 while holding beta fixed and then use optim() again to find beta while holding the other variables fixed. But eventually, I have to run optim on the unmodified likelihood function above and it is very slow, taking several days for large problems. I have also tried metrop() in mcmc, but I find this needs to be very close to the mode of the likelihood to be efficient (in fact, MCMCpack's metropolis function calls optim first and even requires it to invert the hessian before even starting the metropolis algorithm, unless we can provide our own covariance matri...

...uch support the data give to each model parameter) * parameter interdependency (to somehow measure effective model complexity) Both I would extract from the MCMC-trace. Sounds simple? It possibly is - just not for me. I compared several MCMC algorithms implemented in R, from Win/OpenBUGS over MCMCmetrop1R (MCMCpack; my current favourite) and metrop (mcmc) to gibbs and rwmetrop (LearnBayes) and gibbs_met (gibbs.met). These implementations differ dramatically in efficiency (MCMCmetrop1R was over 20 times faster than gibbs_met). Since my functions can be complex (mainly ODEs, complex environmental...

...in Package RandomForest (Liaw, Andy) 33. Re: turning comma separated string from multiple choices into flags (Peter Dalgaard) 34. Re: density estimate (Eik Vettorazzi) 35. Re: turning comma separated string from multiple choices into flags (June Kim) 36. Acceptance rate in metrop (Xia Wang) 37. Re: turning comma separated string from multiple choices into flags (Peter Dalgaard) 38. ggplot 2 - editing in the "panel_1_1" viewport (Pedro Barros) 39. Sending Notes email out of R under windows (popsmelove) 40. Re: adjusting textsize and spacing in mosai...