adaptMCMC (version 1.5)

MCMC.add.samples: Add samples to an existing chain.

Description

Add samples to an existing chain produced by MCMC or MCMC.parallel.

Usage

MCMC.add.samples(MCMC.object, n.update, ...)

Value

A updated version of MCMC.object.

Arguments

MCMC.object

a list produced by MCMC or MCMC.parallel with option list = TRUE.

n.update

number of additional samples.

...

further arguments passed to p.

Author

Andreas Scheidegger, or

Details

Only objects generated with the option list = TRUE can be updated.

A list of chains produced by MCMC.parallel can be updated. However, the calculations are not performed in parallel (i.e. only a single CPU is used).

See Also

MCMC, MCMC.parallel

Examples

## ----------------------
## Banana shaped distribution

## log-pdf to sample from
p.log <- function(x) {
  B <- 0.03                              # controls 'bananacity'
  -x[1]^2/200 - 1/2*(x[2]+B*x[1]^2-100*B)^2
}


## ----------------------
## generate 200  samples

samp <- MCMC(p.log, n=200, init=c(0, 1), scale=c(1, 0.1),
               adapt=TRUE, acc.rate=0.234, list=TRUE)


## ----------------------
## add 200 to the existing chain
samp <- MCMC.add.samples(samp, n.update=200)

str(samp)