BAMBI (version 2.3.5)

summary.angmcmc: Summary statistics for parameters from an angmcmc object

Description

Summary statistics for parameters from an angmcmc object

Usage

# S3 method for angmcmc
summary(object, par.name, comp.label, chain.no, ...)

Value

Returns a list with elements estimate, lower, upper, llik and lpd. estimate

is itself a list with three elements: mean, median and mode providing the sample mean, sample median and (sample) MAP estimates.

Note that summary.angmcmc has its own print method, providing a table the estimated mean and 95% credible intervals for each parameter

Arguments

object

angular MCMC object.

par.name

vector of names of parameters for which point estimates are to be computed. If NULL, results for all parameters are provided.

comp.label

vector of component labels (positive integers, e.g., 1, 2, ...) for which point estimates are to be computed. If NULL, results for all components are provided.

chain.no

vector of chain numbers whose samples are to be be used. in the estimation. By default all chains are used.

...

additional arguments affecting the summary produced.

Details

Computes (after thinning and discarding burn-in) point estimates with 95% posterior credible sets for all components and all parameters, together with the sample averages of log likelihood and log posterior density.

Examples

# illustration only - more iterations needed for convergence
fit.vmsin.20 <- fit_vmsinmix(tim8, ncomp = 3, n.iter =  20,
                             n.chains = 1)
summary(fit.vmsin.20)