plotPointStats: Plot point statistics for each chain

In USGS-R/GcClust: Clustering geochemical data with HMC sampling

Plot point statistics for each chain

Description

Plot point statistics for each chain. The point statistics are calculated and plotted for element 1 of the two mean vectors, element 1 of the two standard deviation vectors, the proportion associated with pdf1, and the log-likelihood.

Usage

plotPointStats(samplePars, procDir = ".", excludedChains = NULL)

Arguments

samplePars	List containing, among other things, the names of the files in which the stanfit objects are stored. These stanfit objects contain the samples of the posterior pdf, which are needed to calculate the point statistics. List samplePars is return by function sampleFmm, for which the documentation includes a complete description of the list.
procDir	Directory containing the files with the stanfit objects.
excludedChains	Vector with the indices of the chains for which the point statistics are not used to calculate plot ranges. See Details.

Details

To prevent a point statistic for a particular Monte Carlo sampling chain from being included in the calculation of the plot range, the index of that chain is specified in argument excludedChains. In other words, the point statistics for all chains are calculated and plotted. If a few chains are specified by argument excludedChains, then the calculation of the plot ranges does not use those specified chains.

The calculation of the point statistics for every chain requires a minute or two.

Examples

## Not run: 
plotPointStats(samplePars)

## End(Not run)

USGS-R/GcClust documentation built on April 17, 2023, 8:08 p.m.