PReMiuM: Dirichlet Process Bayesian Clustering, Profile Regression

Share:

Bayesian clustering using a Dirichlet process mixture model. This model is an alternative to regression models, non-parametrically linking a response vector to covariate data through cluster membership. The package allows Bernoulli, Binomial, Poisson, Normal, survival and categorical response, as well as Normal and discrete covariates. It also allows for fixed effects in the response model, where a spatial CAR (conditional autoregressive) term can be also included. Additionally, predictions may be made for the response, and missing values for the covariates are handled. Several samplers and label switching moves are implemented along with diagnostic tools to assess convergence. A number of R functions for post-processing of the output are also provided. In addition to fitting mixtures, it may additionally be of interest to determine which covariates actively drive the mixture components. This is implemented in the package as variable selection.

Author
David I. Hastie <david.hastie@rsimony.com>, Silvia Liverani <liveranis@gmail.com> and Sylvia Richardson <sylvia.richardson@mrc-bsu.cam.ac.uk> with contributions from Aurore J. Lavigne, Lucy Leigh, Lamiae Azizi
Date of publication
2016-02-23 23:02:17
Maintainer
Silvia Liverani <liveranis@gmail.com>
License
GPL-2
Version
3.1.3
URLs

View on CRAN

Man pages

calcAvgRiskAndProfile
Calculation of the average risks and profiles
calcDissimilarityMatrix
Calculates the dissimilarity matrix
calcOptimalClustering
Calculation of the optimal clustering
calcPredictions
Calculates the predictions
clusSummaryBernoulliDiscrete
Sample datasets for profile regression
computeRatioOfVariance
computeRatioOfVariance
generateSampleDataFile
Generate sample data files for profile regression
globalParsTrace
Plot of the trace of some of the global parameters
heatDissMat
Plot the heatmap of the dissimilarity matrix
is.wholenumber
Function to check if a number is a whole number
mapforGeneratedData
Map generated data
margModelPosterior
Marginal Model Posterior
plotPredictions
Plot the conditional density using the predicted scenarios
plotRiskProfile
Plot the Risk Profiles
PReMiuM-package
Dirichlet Process Bayesian Clustering
profRegr
Profile Regression
setHyperparams
Definition of characteristics of sample datasets for profile...
summariseVarSelectRho
summariseVarSelectRho
vec2mat
Vector to upper triangular matrix

Files in this package

PReMiuM
PReMiuM/inst
PReMiuM/inst/CITATION
PReMiuM/src
PReMiuM/src/Makevars
PReMiuM/src/postProcess.cpp
PReMiuM/src/PReMiuM.cpp
PReMiuM/src/Makevars.win
PReMiuM/src/include
PReMiuM/src/include/postProcess.h
PReMiuM/src/include/PReMiuMData.h
PReMiuM/src/include/PReMiuMOptions.h
PReMiuM/src/include/PReMiuMArs.h
PReMiuM/src/include/PReMiuMModel.h
PReMiuM/src/include/PReMiuMProposals.h
PReMiuM/src/include/MCMC
PReMiuM/src/include/MCMC/model.h
PReMiuM/src/include/MCMC/chain.h
PReMiuM/src/include/MCMC/state.h
PReMiuM/src/include/MCMC/proposal.h
PReMiuM/src/include/MCMC/sampler.h
PReMiuM/src/include/PReMiuMArs.cpp
PReMiuM/src/include/PReMiuMIO.h
PReMiuM/src/include/Math
PReMiuM/src/include/Math/random.h
PReMiuM/src/include/Math/Error.h
PReMiuM/src/include/Math/ars2.h
PReMiuM/src/include/Math/mathfunctions.h
PReMiuM/src/include/Math/distribution.h
PReMiuM/NAMESPACE
PReMiuM/R
PReMiuM/R/postProcess.R
PReMiuM/R/generateData.R
PReMiuM/MD5
PReMiuM/DESCRIPTION
PReMiuM/ChangeLog
PReMiuM/man
PReMiuM/man/computeRatioOfVariance.Rd
PReMiuM/man/vec2mat.Rd
PReMiuM/man/setHyperparams.Rd
PReMiuM/man/margModelPosterior.Rd
PReMiuM/man/globalParsTrace.Rd
PReMiuM/man/PReMiuM-package.Rd
PReMiuM/man/is.wholenumber.Rd
PReMiuM/man/clusSummaryBernoulliDiscrete.Rd
PReMiuM/man/calcAvgRiskAndProfile.Rd
PReMiuM/man/mapforGeneratedData.Rd
PReMiuM/man/plotPredictions.Rd
PReMiuM/man/heatDissMat.Rd
PReMiuM/man/generateSampleDataFile.Rd
PReMiuM/man/calcOptimalClustering.Rd
PReMiuM/man/calcDissimilarityMatrix.Rd
PReMiuM/man/profRegr.Rd
PReMiuM/man/calcPredictions.Rd
PReMiuM/man/plotRiskProfile.Rd
PReMiuM/man/summariseVarSelectRho.Rd