multi_hpd: Bayesian HPD regions for a series of MCMC chains

In ArchaeoPhases: Post-Processing of the Markov Chain Simulated by 'ChronoModel', 'Oxcal' or 'BCal'

Bayesian HPD regions for a series of MCMC chains

Description

Estimation of the highest posterior density regions for each variable of a simulated Markov chain. This function uses the hdr() function included in the hdrcde package. An HPD region may be a union of several intervals.

Usage

multi_hpd(data, position, level = 0.95, round_to = 0)

Arguments

data	Data frame containing the output of the MCMC algorithm.
position	Numeric vector containing the position of the column corresponding to the MCMC chains of interest.
level	Probability corresponding to the level of confidence.
round_to	Integer indicating the number of decimal places.

Details

Highest posterior density function region using the function hdr() from the hdrcd package

Value

Returns a list with the following components:

results

A data frame where the rows correspond to the columns in the selected data set and the columns labeled inf and sup correspond to the lower and upper endpoints of each highest posterior density interval, respectively.

level

Probability corresponding to the level of confidence.

call

The function call.

matrix of values containing the level of confidence and for each variable of the MCMC chain. The name of the resulting rows are the positions of the corresponding columns in the CSV file. The result is given in calendar years (BC/AD).

Author(s)

Anne Philippe, [e-mail] and

Marie-Anne Vibet, [e-mail]

References

Hyndman, R.J. (1996) Computing and graphing highest density regions. American Statistician, 50, 120-126.

Examples

  data(Events)
  multi_hpd(Events, c(2, 4, 3), 0.95)

ArchaeoPhases documentation built on June 22, 2022, 1:05 a.m.