numOSL (version 1.6)

mcFMM: Estimating parameters of a finite mixture age model (central age model) with a Markov chain Monte Carlo method

Description

Sampling from the joint-likelihood function of a finite mixture age model (central age model) using a Markov chain Monte Carlo method.

Usage

mcFMM(EDdata, ncomp = 1, addsigma = 0, iflog = TRUE, 
      nsim = 50000, inis = list(), control.args = list())

Arguments

EDdata

matrix(required): two columns, i.e., equivalent doses and associated errors

ncomp

numeric(with default): the number of components (1 means a central age model)

addsigma

numeric(with default): additional uncertainty

iflog

logical(with default): use log-scale or not

nsim

numeric(with default): the deseried total number of iterations

inis

list(with default): initials of the chain. Example, inis=list(p1=1,p2=1,mu1=5,mu2=10) in FMM2

control.args

list(with default): arguments used in a slice sampling method, see details

Value

• Return an invisible list of S3 class "mcAgeModels" including following elements, which can be operated with function reportSAM:
• EDdata
  equivalent dose values
• addsigma
  additional uncertainty
• model
  the fitting model
• iflog
  use log-scale or not
• nsim
  the number of iterations
• chains
  the simulated quantities of interest

Details

This function is used to sampling from the joint-likelihood function of a finite mixture age model (central age model) using a Markov chain Monte Carlo method called slice sampling (Neal, 2003). Three arguments (control.args) are used to control the performance of the sampling process: w: the size of the steps for creating an interval from which to sample, default w=1 m: the limit on steps for expanding an interval, the interval is expanded to include more feasible values if possible. m<=1< code=""> means no limit on the expandation, m>1 means that the interval is expanded with a finite number of iterations. Default m=-100 nstart: the allowed maximum number of trials for updating a variable in each iteration. It can be used to monitor the stability of the chains of a model. For example, the chain of MAM4 is very likely to crash down and sometimes more number of attempts (nstart>1) is needed to complete the simulation. Default nstart=1

References

Galbraith RF, Green P, 1990. Estimating the component ages in a finite mixture. International Journal of Radiation Applications and Instrumentation. Part D. Nuclear Tracks and Radiation Measurements, 17: 197-206.

Neal RM, 2003. "Slice sampling" (with discussion). Annals of Statistics, 31: 705-767. Software is available at http://www.cs.utoronto.ca/~radford/slice.software.html.

See Also

mcMAM; reportSAM; RadialPlotter

Examples

data(EDdata)
  # Construct MCMC chains for a 3-component FMM.
  obj<-mcFMM(EDdata$gl11,ncomp=3,nsim=5000)
  reportSAM(obj,thin=2,burn=1e3)