R: Reporting MCMC outputs for statistical age models

reportMC {numOSL}

R Documentation

Reporting MCMC outputs for statistical age models

Description

Summarizing distributions of parameters simulated from statistical age models using a Markov Chain Monte Carlo method.

Usage

reportMC(obj, burn = 10000, thin = 5, 
         plot = TRUE, outfile = NULL, ...)

Arguments

`obj`	list(required): an object of S3 class `"mcAgeModels"`, which is produced by function mcFMM or mcMAM
`burn`	integer(with default): number of iterations (i.e., the initial, non-stationary portion of the chain) to be discarded
`thin`	integer(with default): take every `thin-th` iteration
`plot`	logical(with default): plot the MCMC output or not
`outfile`	character(optional): if specified, simulated parameters will be written to a CSV file named `"outfile"` and saved to the current work directory
`...`	do not use

Details

Function reportMC summarizes the output of a Markov Chain (the mean values, the standard deviations, the mode values, and the 2.5, 25, 50, 75, 97.5 quantiles of the simulated parameters). The initial i (burn=i) samples may have been affected by the inital state and has to be discarded ("burn-in"). Autocorrelation of simulated samples can be reduced by taking every j-th (thin=j) iteration ("thining").

Value

Return a list that contains the following elements:

`pars`	means, standard deviations, and modes of simulated parameters
`quantile`	quantiles of simulated parameters
`maxlik`	maximum logged likelihood values calculated using the means and modes of simulated parameters
`bic`	Bayesian Information Criterion (BIC) values calculated using the means and modes of simulated parameters

References

Lunn D, Jackson C, Best N, Thomas A, Spiegelhalter D, 2013. The BUGS book: a practical introduction to bayesian analysis. Chapman & Hall/CRC Press.

Gelman A, Carlin JB, Stern HS, Dunson DB, Vehtari A, Rubin DB, 2013. Bayesian data analysis. Chapman & Hall/CRC Press.

Peng J, Dong ZB, Han FQ, 2016. Application of slice sampling method for optimizing OSL age models used for equivalent dose determination. Progress in Geography, 35(1): 78-88. (In Chinese).