Statistics package

The statistics package is part of the Octave Forge project.

Core package

We need to decide what to do with the functions in the existing forge package when:

To be decided

function	decision/notes
anderson_darling_cdf
cl_multinom
dcov
gevfit_lmom
iwishpdf
jsucdf
jsupdf
monotone_smooth
normalise_distribution
princomp	matlab says that the function has been removed but likely is a lie. We should keep it too.
qrandn
runstest
sigma_pts	not yet released
violin
vmpdf
vmrnd
wishpdf

Matlab incompatible

These functions have the same name as Matlab functions but have a different interface

• boxplot
• gpcdf
• gpinv
• gppdf
• gprnd

Can be reused in other functions

forge function	matlab counterpart
anderson_darling_test	adtest
bbscdf	BirnbaumSaundersDistribution class
bbsinv	BirnbaumSaundersDistribution class
bbspdf	BirnbaumSaundersDistribution class
bbsrnd	BirnbaumSaundersDistribution class
binotest	binofit
burrcdf	BurrDistribution class
burrinv	BurrDistribution class
burrpdf	BurrDistribution class
burrrnd	BurrDistribution class
nakacdf	NakagamiDistribution class
nakainv	NakagamiDistribution class
nakapdf	NakagamiDistribution class
nakarnd - should be used to implement the	NakagamiDistribution class
regress_gp	RegressionGP class
repanova	RepeatedMeasuresModel.ranova
tricdf	TriangularDistribution class
triinv	TriangularDistribution class
tripdf	TriangularDistribution class
trirnd	TriangularDistribution class
logistic_cdf	LogisticDistribution class
logistic_inv	LogisticDistribution class
logistic_pdf	LogisticDistribution class
logistic_rnd	LogisticDistribution class
stdnormal_cdf	NormalDistribution class
stdnormal_inv	NormalDistribution class
stdnormal_pdf	NormalDistribution class
stdnormal_rnd	NormalDistribution class
anova	anova method in different *Model classes
manova	manova methods in different *Model classes
bartlett_test	barttest
kolmogorov_smirnov_test	ktest
kolmogorov_smirnov_test_2	ktest2
kruskal_wallis_test	kruskalwallis

Ready to go

These functions seem to be matlab compatible

• anovan
• betastat
• binostat
• binotest
• canoncorr
• caseread
• casewrite
• cdf
• chi2stat
• cmdscale
• combnk
• copulacdf
• copulapdf
• copularnd
• crossval
• @cvpartition
• dendrogram
• expstat
• ff2n
• fitgmdist
• fstat
• fullfact
• gamfit
• gamlike
• gamstat
• geomean
• geostat
• gevcdf
• gevfit
• gevinv
• gevlike
• gevpdf
• gevrnd
• gevstat
• gmdistribution
• grp2idx
• harmmean
• hist3
• histfit
• hmmestimate
• hmmgenerate
• hmmviterbi
• hygestat
• iwishrnd
• jackknife
• kmeans
• linkage
• lognstat
• mad
• mahal
• mnpdf
• mnrnd
• mvncdf
• mvnpdf
• mvnrnd
• mvtcdf
• mvtpdf
• mvtrnd
• nanmax
• nanmean
• nanmedian
• nanmin
• nanstd
• nansum
• nanvar
• nbinstat
• normplot
• normstat
• pcacov
• pcares
• pdf
• pdist2
• pdist
• plsregress
• poisstat
• random
• randsample
• raylcdf
• raylinv
• raylpdf
• raylrnd
• raylstat
• regress
• signtest
• squareform
• stepwisefit
• tabulate
• tblread
• tblwrite
• trimmean
• tstat
• ttest2
• ttest
• unidstat
• unifstat
• vartest2
• vartest
• wblstat
• wishrnd
• ztest
• prctile
• qqplot
• betacdf
• betainv
• betapdf
• betarnd
• binocdf
• binoinv
• binopdf
• binornd
• chi2cdf
• chi2inv
• chi2pdf
• chi2rnd
• expcdf
• expinv
• exppdf
• exprnd
• fcdf
• finv
• fpdf
• frnd
• gamcdf
• gaminv
• gampdf
• gamrnd
• geocdf
• geoinv
• geopdf
• geornd
• hygecdf
• hygeinv
• hygepdf
• hygernd
• logncdf
• logninv
• lognpdf
• lognrnd
• nbincdf
• nbininv
• nbinpdf
• nbinrnd
• normcdf
• norminv
• normpdf
• normrnd
• poisscdf
• poissinv
• poisspdf
• poissrnd
• tcdf
• tinv
• tpdf
• trnd
• unidcdf
• unidinv
• unidpdf
• unidrnd
• unifcdf
• unifinv
• unifpdf
• unifrnd
• wblcdf
• wblinv
• wblpdf
• wblrnd

Development

Follows an incomplete list of stuff missing in the statistics package to be matlab compatible. Bugs are not listed here, search and report them on the bug tracker instead.

this entire section is about the current development version. If a Matlab function is missing from the list and does not appear on the current release of the package, confirm that is also missing in the development sources before adding it.

Missing functions

• ClassificationBaggedEnsemble
• ClassificationDiscriminant
• ClassificationDiscriminant.fit
• ClassificationEnsemble
• ClassificationKNN
• ClassificationKNN.fit
• ClassificationPartitionedEnsemble
• ClassificationPartitionedModel
• ClassificationTree
• ClassificationTree.fit
• CompactClassificationDiscriminant
• CompactClassificationEnsemble
• CompactClassificationTree
• CompactRegressionEnsemble
• CompactRegressionTree
• CompactTreeBagger
• ExhaustiveSearcher
• GeneralizedLinearModel
• GeneralizedLinearModel.fit
• GeneralizedLinearModel.stepwise
• KDTreeSearcher
• LinearMixedModel
• LinearMixedModel.fit
• LinearMixedModel.fitmatrix
• LinearModel
• LinearModel.fit
• LinearModel.stepwise
• NaiveBayes
• NaiveBayes.fit
• NonLinearModel
• NonLinearModel.fit
• ProbDistUnivKernel
• ProbDistUnivParam
• RegressionBaggedEnsemble
• RegressionEnsemble
• RegressionPartitionedEnsemble
• RegressionPartitionedModel
• RegressionTree
• RegressionTree.fit
• TreeBagger
• addTerms
• addedvarplot
• addlevels
• adtest
• andrewsplot
• anova1
• anova2
• ansaribradley
• aoctool
• barttest
• bbdesign
• betafit
• betalike
• binofit
• biplot
• bootci
• bootstrp
• candexch
• candgen
• capability
• capaplot
• ccdesign
• cdfplot
• cell2dataset
• chi2gof
• cholcov
• classify
• classregtree
• cluster
• clusterdata
• clustering.evaluation.CalinskiHarabaszEvaluation
• clustering.evaluation.DaviesBouldinEvaluation
• clustering.evaluation.GapEvaluation
• clustering.evaluation.SilhouetteEvaluation
• coefCI
• coefTest
• compact
• compare
• confusionmat
• controlchart
• controlrules
• cophenet
• copulafit
• copulaparam
• copulastat
• cordexch
• corrcov
• covarianceParameters
• coxphfit
• createns
• crosstab
• datasample
• dataset
• dataset2cell
• dataset2struct
• dataset2table
• datasetfun
• daugment
• dcovary
• designMatrix
• devianceTest
• dfittool
• disttool
• droplevels
• dummyvar
• dwtest
• ecdf
• ecdfhist
• evalclusters
• evcdf
• evfit
• evinv
• evlike
• evpdf
• evrnd
• evstat
• explike
• export
• factoran
• fitdist
• fitensemble
• fitglm
• fitlm
• fitlme
• fitlmematrix
• fitnlm
• fitted
• fixedEffects
• fracfact
• fracfactgen
• friedman
• fsurfht
• gagerr
• getlabels
• getlevels
• gline
• glmfit
• glmval
• glyphplot
• gname
• gpcdf
• gpfit
• gpinv
• gplike
• gplotmatrix
• gppdf
• gprnd
• gpstat
• grpstats
• gscatter
• haltonset
• hmmdecode
• hmmtrain
• hougen
• icdf
• inconsistent
• interactionplot
• invpred
• islevel
• ismissing
• isundefined
• jbtest
• johnsrnd
• join
• knnsearch
• kruskalwallis
• ksdensity
• kstest
• kstest2
• labels
• lasso
• lassoPlot
• lassoglm
• levelcounts
• leverage
• lhsdesign
• lhsnorm
• lillietest
• linhyptest
• lognfit
• lognlike
• lsline
• mahal
• maineffectsplot
• makedist
• manova1
• manovacluster
• mat2dataset
• mdscale
• mergelevels
• mhsample
• mle
• mlecov
• mnrfit
• mnrval
• multcompare
• multivarichart
• mvregress
• mvregresslike
• nancov
• nbinfit
• ncfcdf
• ncfinv
• ncfpdf
• ncfrnd
• ncfstat
• nctcdf
• nctinv
• nctpdf
• nctrnd
• nctstat
• ncx2cdf
• ncx2inv
• ncx2pdf
• ncx2rnd
• ncx2stat
• negloglik
• nlinfit
• nlintool
• nlmefit
• nlmefitsa
• nlparci
• nlpredci
• nnmf
• nominal
• normfit
• normlike
• normspec
• optimalleaforder
• ordinal
• parallelcoords
• paramci
• paretotails
• partialcorr
• partialcorri
• pca
• pdf
• pearsrnd
• perfcurve
• plotAdded
• plotAdjustedResponse
• plotDiagnostics
• plotEffects
• plotInteraction
• plotResiduals
• plotSlice
• poissfit
• polytool
• ppca
• predict
• prob.BetaDistribution
• prob.BinomialDistribution
• prob.BirnbaumSaundersDistribution
• prob.BurrDistribution
• prob.ExponentialDistribution
• prob.ExtremeValueDistribution
• prob.GammaDistribution
• prob.GeneralizedExtremeValueDistribution
• prob.GeneralizedParetoDistribution
• prob.InverseGaussianDistribution
• prob.KernelDistribution
• prob.LogisticDistribution
• prob.LoglogisticDistribution
• prob.LognormalDistribution
• prob.MultinomialDistribution
• prob.NakagamiDistribution
• prob.NegativeBinomialDistribution
• prob.NormalDistribution
• prob.PiecewiseLinearDistribution
• prob.PoissonDistribution
• prob.RayleighDistribution
• prob.RicianDistribution
• prob.TriangularDistribution
• prob.UniformDistribution
• prob.WeibullDistribution
• prob.tLocationScaleDistribution
• probplot
• procrustes
• proflik
• qrandset
• qrandstream
• randomEffects
• randtool
• rangesearch
• ranksum
• raylfit
• rcoplot
• refcurve
• refline
• regstats
• relieff
• removeTerms
• residuals
• response
• ridge
• robustdemo
• robustfit
• rotatefactors
• rowexch
• rsmdemo
• rstool
• sampsizepwr
• scatterhist
• sequentialfs
• setlabels
• signrank
• silhouette
• slicesample
• sobolset
• statget
• statset
• step
• stepwise
• stepwiseglm
• stepwiselm
• struct2dataset
• surfht
• svmclassify
• svmtrain
• table2dataset
• tabulate
• tdfread
• tiedrank
• truncate
• unifit
• vartestn
• wblfit
• wbllike
• wblplot
• x2fx
• xptread