mcmcapply: Calculations on 'mcmc.list' objects
In dclone: Data Cloning and MCMC Tools for Maximum Likelihood Methods

Description Usage Arguments Details Value Author(s) Examples

Conveniently calculates statistics for mcmc.list objects.

1
2
3

mcmcapply(x, FUN, ...)
## S3 method for class 'mcmc.list'
stack(x, ...)

`x`	Objects of class `mcmc.list`.
`FUN`	A function to be used in the calculations, returning a single value.
`...`	Other arguments passed to `FUN`.

mcmcapply returns a certain statistics based on FUN after coercing into a matrix. FUN can be missing, in this case mcmcapply is equivalent to calling as.matrix on an 'mcmc.list' object.

stack can be used to concatenates 'mcmc.list' objects into a single vector along with index variables indicating where each observation originated from (e.g. iteration, variable, chain).

mcmcapply returns statistic value for each variable based on FUN, using all values in all chains of the MCMC object.

stack returns a data frame with columns: iter, variable, chain, value.

Peter Solymos, solymos@ualberta.ca

data(regmod)
mcmcapply(regmod, mean)
mcmcapply(regmod, sd)

x <- stack(regmod)
head(x)
summary(x)
library(lattice)
xyplot(value ~ iter | variable, data=x,
    type="l", scales = "free", groups=chain)