plotPointProc-method: Plot the point process of the component parameters

In simonsays1980/finmix: An R package for Bayesian estimation of finite mixture distributions

Description

Calling plotPointProc() on an object of class mcmcoutput or mcmcoutputperm plots the point process of the sampled component parameters from MCMC sampling, either the original parameters or the relabeled ones.

Arguments

x	An mcmcoutput or mcmcoutputperm object containing all sampled values.
dev	A logical indicating, if the plots should be shown by a graphical device. If plots should be stored to a file set dev to FALSE.
...	Further arguments to be passed to the plotting function.

Details

The point process is used to identify the number of components in the underlying distribution of the data for mixtures with unknown number of components (see Frühwirth-Schnatter (2006, Subsection 3.7.1)). The number of clusters that evolve in the plot give a hint on the true number of components in the mixture distribution. The MCMC draws will scatter around the points corresponding to the true point process of the mixture model. The spread of the clusters represent the uncertainty of estimating the points.

For mixtures with univariate component parameters (e.g. Poisson, Exponential) the component parameters are plotted against draws from a standard normal distribution. For mixtures with bivariate component parameters (e.g. Normal) the first parameters are plotted against the second ones. For mixtures with multivariate component parameters a point process for each type of mixture model is plotted.

Note that this method for mcmcoutputperm objects is only implemented for mixtures of Poisson and Binomial distributions.

Value

The point process of the MCMC samples.

See Also

• mixturemcmc() for performing MCMC sampling

• mcmcpermute() for permuting MCMC samples

• plotTraces() for plotting the traces of sampled values

• plotHist() for plotting histograms of sampled values

• plotDens() for plotting densities of sampled values

• plotSampRep() for plotting sampling representations of sampled values

• plotPostDens() for plotting posterior densities for sampled values

Examples

# Define a Poisson mixture model with two components.
f_model <- model("poisson", par = list(lambda = c(0.3, 1.2)), K = 2)
# Simulate data from the mixture model.
f_data <- simulate(f_model)
# Define the hyper-parameters for MCMC sampling.
f_mcmc <- mcmc()
# Define the prior distribution by relying on the data.
f_prior <- priordefine(f_data, f_model)
# Start MCMC sampling.
f_output <- mixturemcmc(f_data, f_model, f_prior, f_mcmc)
f_outputperm <- mcmcpermute(f_output)
plotPointProc(f_outputperm)

simonsays1980/finmix documentation built on Dec. 23, 2021, 2:25 a.m.