PReMiuM (version 3.2.13)

globalParsTrace: Plot of the trace of some of the global parameters

Description

Function to lot the trace of some global parameters

Usage

globalParsTrace(runInfoObj, parameters = "nClusters",plotBurnIn=FALSE,whichBeta=1)

Value

Plot of trace of some global parameters.

Arguments

This function allows to visualise the trace of the global parameters.

Note that this function has not been optimised for large datasets.

runInfoObj

An object of class runInfoObj.

parameters

The parameter whose trace will be plotted. This can be set equal to "nClusters" (default), "alpha", "mpp" and "beta", as by the model. As beta can be a vector, we advise to also set the option "whichBeta" below to select which fixed effect parameter to visualise in the plot. "mpp" stands for marginal partition posterior, also referred to as marginal model posterior.

plotBurnIn

Set to FALSE (default) it does not plot the trace for the burn in period. Set to TRUE it plots the trace including the burn in period.

whichBeta

Integer which selects which fixed effect parameter is plotted.

Authors

Silvia Liverani, Department of Epidemiology and Biostatistics, Imperial College London and MRC Biostatistics Unit, Cambridge, UK

Maintainer: Silvia Liverani <[e-mail]>

References

Silvia Liverani, David I. Hastie, Lamiae Azizi, Michail Papathomas, Sylvia Richardson (2015). PReMiuM: An R Package for Profile Regression Mixture Models Using Dirichlet Processes. Journal of Statistical Software, 64(7), 1-30. tools:::Rd_expr_doi("10.18637/jss.v064.i07").

Examples

if (FALSE) {
# generate simulated dataset
generateDataList <- clusSummaryBernoulliDiscreteSmall()
inputs <- generateSampleDataFile(generateDataList)

# run profile regression
runInfoObj<-profRegr(yModel=inputs$yModel, xModel=inputs$xModel, 
 nSweeps=10, nBurn=20, data=inputs$inputData, output="output", nFilter=3,
 covNames=inputs$covNames,nClusInit=15,reportBurnIn=FALSE,
 fixedEffectsNames = inputs$fixedEffectNames)

# plot trace for alpha
globalParsTrace(runInfoObj,parameters="alpha",plotBurnIn=FALSE)
}