getsamples: Extract matrix of samples from a 'metrosamp' object
In JGCRI/metrosamp: Basic Metropolis Sampler for Markov Chain Monte Carlo

Description Usage Arguments Details Value

View source: R/util.R

Given a metrosamp object, or a list of metrosamp objects, extract the matrix of parameter samples. Optionally, also extract the log-posterior values.

1	getsamples(mcruns, thinto = NULL, includelp = FALSE)

`mcruns`	A `metrosamp` object or a list of `metrosamp` objects.
`thinto`	Total number of samples to thin the sample array to. Many analysis operations scale as O(N) or O(N \ln N), so thinning can speed these up pretty substantially, especially for runs with poor sampling efficiency.
`includelp`	If true, return the log-posterior values in a list with the sample matrix.

If the input is a list of metrosamp objects, then their samples are merged into a single grand matrix of results. Doing this discards the information about which samples came from which Markov chains.

If includelp is FALSE, a matrix of samples, otherwise, a list with the sample matrix and the vector of log-posterior values.

JGCRI/metrosamp documentation built on Aug. 8, 2019, 10:59 p.m.