R/AllClasses-09-Prior-hierarchy.R
In StatisticsNZ/demest: Bayesian Demographic Estimation and Forecasting
setClass("Prior",
contains = c("VIRTUAL",
"SlotsToExtract",
"IMethodPrior",
"ComponentFlagsMixin",
"IsSaturatedMixin",
"JMixin"))
setClass("Exch",
contains = c("VIRTUAL",
"Prior",
"AllStrucZeroMixin"))
setClass("DLM",
contains = c("VIRTUAL",
"Prior",
"AAlphaMixin",
"AllStrucZeroMixin",
"AlongAllStrucZeroMixin",
"AlphaDLMMixin",
"IAlongMixin",
"IteratorStateMixin",
"IteratorVMixin",
"KLMixin",
"NuAlphaMixin",
"OmegaAlphaMixin",
"OmegaAlphaMaxMixin",
"PhiMixin",
"PhiKnownMixin",
"PhiMinMaxMixin",
"Shape1Shape2PhiMixin"))
setClass("ICAR",
contains = c("VIRTUAL",
"Prior",
"AlphaICARMixin"))
setClass("Known",
contains = c("VIRTUAL",
"Prior",
"AllStrucZeroMixin",
"AlphaKnownMixin",
"AlphaKnownAllMixin",
"MetadataAllMixin"),
validity = function(object) {
alphaKnown <- object@alphaKnown@.Data
J <- object@J@.Data
isSaturated <- object@isSaturated@.Data
allStrucZero <- object@allStrucZero
## 'alphaKnown' has length 'J'
if (!identical(length(alphaKnown), J))
return(gettextf("'%s' does not have length '%s'",
"alphaKnown", "J"))
## is not saturated
if (isSaturated)
return(gettextf("prior has class \"%s\" but '%s' is %s",
"Known", "isSaturated", "TRUE"))
## 'alphaKnown' is zero if 'allStrucZero' is TRUE
if (any(allStrucZero & (alphaKnown != 0)))
return(gettextf("elements where '%s' is %s but '%s' does not equal %d",
"allStrucZero", "TRUE", "alphaKnown", 0L))
TRUE
})
setClass("Mix",
contains = c("VIRTUAL",
"Prior",
"AComponentWeightMixMixin",
"ALevelComponentWeightMixMixin",
"aMixMixin",
"AVectorsMixMixin",
"AllStrucZeroMixin",
"AlphaMixMixin",
"CMixMixin",
"ComponentWeightMixMixin",
"DimBetaMixin",
"IAlongMixin",
"FoundIndexClassMaxPossibleMixMixin",
"IndexClassMaxMixMixin",
"IndexClassMaxPossibleMixMixin",
"IndexClassMaxUsedMixMixin",
"IndexClassMixMixin",
"IndexClassProbMixMixin",
"IteratorProdVectorMix",
"IteratorsDimsMixMixin",
"LatentWeightMixMixin",
"LatentComponentWeightMixMixin",
"LevelComponentWeightMinMaxMixin",
"LevelComponentWeightMixMixin",
"mMixMixin",
"MeanLevelComponentWeightMixMixin",
"NuComponentWeightMixMixin",
"NuLevelComponentWeightMixMixin",
"NuVectorsMixMixin",
"OmegaComponentWeightMaxMixMixin",
"OmegaComponentWeightMixMixin",
"OmegaLevelComponentWeightMaxMixMixin",
"OmegaLevelComponentWeightMixMixin",
"OmegaVectorsMaxMixMixin",
"OmegaVectorsMixMixin",
"PhiKnownMixin",
"PhiMinMaxMixin",
"PhiMixMixin",
"PosProdVectorsMixMixin",
"PriorMeanLevelComponentWeightMixMixin",
"PriorSDLevelComponentWeightMixMixin",
"ProdVectorsMixMixin",
"RMixMixin",
"Shape1Shape2PhiMixin",
"SumsWeightsMixMixin",
"ToleranceMixin",
"VectorsMixMixin",
"WeightMixMixin",
"YXXXMixMixin"),
validity = function(object) {
## at least 2 dimensions
TRUE
})
## TimeInvariant
setClass("TimeInvariant",
prototype = prototype(iMethodPrior = -1L,
slotsToExtract = character(),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", TRUE),
isSaturated = methods::new("LogicalFlag", FALSE)),
contains = "Prior",
validity = function(object) {
isSaturated <- object@isSaturated@.Data
## is not saturated
if (isSaturated)
return(gettextf("prior has class \"%s\" but '%s' is %s",
"TimeInvariant", "isSaturated", "TRUE"))
TRUE
})
## ExchFixed
setClass("ExchFixed",
prototype = prototype(iMethodPrior = 0L,
slotsToExtract = character(),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", TRUE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
J = methods::new("Length", 1L),
mean = methods::new("Parameter", 0),
tau = methods::new("Scale", 1)),
contains = c("Prior",
"AllStrucZeroMixin",
"MeanMixin",
"TauMixin"),
validity = function(object) {
isSaturated <- object@isSaturated@.Data
## is not saturated
if (isSaturated)
return(gettextf("prior has class \"%s\" but '%s' is %s",
"Known", "isSaturated", "TRUE"))
TRUE
})
setClassUnion("Exchangeable",
members = c("Exch", "ExchFixed"))
## Exch
setClass("ExchNormZero",
prototype = prototype(iMethodPrior = 1L,
slotsToExtract = "tau",
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Exch",
"NormMixin",
"ZeroMixin"))
setClass("ExchNormCov",
prototype = prototype(iMethodPrior = 2L,
slotsToExtract = c("eta", "tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Exch",
"CovariatesMixin",
"NormMixin"))
setClass("ExchRobustZero",
prototype = prototype(iMethodPrior = 3L,
slotsToExtract = "tau",
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Exch",
"RobustMixin",
"ZeroMixin"))
setClass("ExchRobustCov",
prototype = prototype(iMethodPrior = 4L,
slotsToExtract = c("eta", "tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Exch",
"CovariatesMixin",
"RobustMixin"))
## DLM, NoTrend
setClass("DLMNoTrendNormZeroNoSeason",
prototype = prototype(iMethodPrior = 5L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"NormMixin",
"NoTrendMixin",
"ZeroMixin"))
setClass("DLMNoTrendNormZeroWithSeason",
prototype = prototype(iMethodPrior = 6L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"s",
"omegaSeason",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"NormMixin",
"NoTrendMixin",
"SeasonMixin",
"ZeroMixin"))
setClass("DLMNoTrendNormCovNoSeason",
prototype = prototype(iMethodPrior = 7L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"CovariatesMixin",
"NormMixin",
"NoTrendMixin"))
setClass("DLMNoTrendNormCovWithSeason",
prototype = prototype(iMethodPrior = 8L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"s",
"omegaSeason",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"CovariatesMixin",
"NormMixin",
"NoTrendMixin",
"SeasonMixin"))
setClass("DLMNoTrendRobustZeroNoSeason",
prototype = prototype(iMethodPrior = 9L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"NoTrendMixin",
"RobustMixin",
"ZeroMixin"))
setClass("DLMNoTrendRobustZeroWithSeason",
prototype = prototype(iMethodPrior = 10L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"s",
"omegaSeason",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"NoTrendMixin",
"RobustMixin",
"SeasonMixin",
"ZeroMixin"))
setClass("DLMNoTrendRobustCovNoSeason",
prototype = prototype(iMethodPrior = 11L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"CovariatesMixin",
"NoTrendMixin",
"RobustMixin"))
setClass("DLMNoTrendRobustCovWithSeason",
prototype = prototype(iMethodPrior = 12L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"s",
"omegaSeason",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"CovariatesMixin",
"NoTrendMixin",
"RobustMixin",
"SeasonMixin"))
## DLM, WithTrend
setClass("DLMWithTrendNormZeroNoSeason",
prototype = prototype(iMethodPrior = 13L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89),
nrow = 2L,
ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89),
nrow = 2L,
ncol = 2L))),
contains = c("DLM",
"NormMixin",
"WithTrendMixin",
"ZeroMixin"))
setClass("DLMWithTrendNormZeroWithSeason",
prototype = prototype(iMethodPrior = 14L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"s",
"omegaSeason",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"NormMixin",
"SeasonMixin",
"WithTrendMixin",
"ZeroMixin"))
setClass("DLMWithTrendNormCovNoSeason",
prototype = prototype(iMethodPrior = 15L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"CovariatesMixin",
"NormMixin",
"WithTrendMixin"))
setClass("DLMWithTrendNormCovWithSeason",
prototype = prototype(iMethodPrior = 16L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"s",
"omegaSeason",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"CovariatesMixin",
"NormMixin",
"SeasonMixin",
"WithTrendMixin"))
setClass("DLMWithTrendRobustZeroNoSeason",
prototype = prototype(iMethodPrior = 17L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"RobustMixin",
"WithTrendMixin",
"ZeroMixin"))
setClass("DLMWithTrendRobustZeroWithSeason",
prototype = prototype(iMethodPrior = 18L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"s",
"omegaSeason",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"RobustMixin",
"SeasonMixin",
"WithTrendMixin",
"ZeroMixin"))
setClass("DLMWithTrendRobustCovNoSeason",
prototype = prototype(iMethodPrior = 19L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
meanDelta = methods::new("Parameter", 0),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"CovariatesMixin",
"RobustMixin",
"WithTrendMixin"))
setClass("DLMWithTrendRobustCovWithSeason",
prototype = prototype(iMethodPrior = 20L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"s",
"omegaSeason",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"CovariatesMixin",
"RobustMixin",
"SeasonMixin",
"WithTrendMixin"))
## ICAR
setClass("ICARNormZero",
prototype = prototype(iMethodPrior = 21L,
slotsToExtract = c("alphaICAR",
"omegaAlpha",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", TRUE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("ICAR",
"NormMixin",
"ZeroMixin"))
setClass("ICARNormCov",
prototype = prototype(iMethodPrior = 22L,
slotsToExtract = c("alphaICAR",
"omegaAlpha",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", TRUE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("ICAR",
"CovariatesMixin",
"NormMixin"))
setClass("ICARRobustZero",
prototype = prototype(iMethodPrior = 23L,
slotsToExtract = c("alphaICAR",
"omegaAlpha",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", TRUE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("ICAR",
"RobustMixin",
"ZeroMixin"))
setClass("ICARRobustCov",
prototype = prototype(iMethodPrior = 24L,
slotsToExtract = c("alphaICAR",
"omegaAlpha",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", TRUE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("ICAR",
"CovariatesMixin",
"RobustMixin"))
## Known
setClass("KnownCertain",
prototype = prototype(iMethodPrior = 29L,
slotsToExtract = character(),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", TRUE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", TRUE)),
contains = "Known")
setClass("KnownUncertain",
prototype = prototype(iMethodPrior = 30L,
slotsToExtract = character(),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", TRUE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", TRUE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE)),
contains = c("Known",
"AKnownVecMixin",
"AKnownAllVecMixin"),
validity = function(object) {
AKnownVec <- object@AKnownVec
J <- object@J@.Data
allStrucZero <- object@allStrucZero
## 'AKnownVec' has length 'J'
if (!identical(length(AKnownVec), J))
return(gettextf("'%s' does not have length '%s'",
"AKnownVec", "J"))
## 'AKnownVec' is zero if 'allStrucZero' is TRUE
if (any(allStrucZero & (AKnownVec != 0)))
return(gettextf("elements where '%s' is %s but '%s' does not equal %d",
"allStrucZero", "TRUE", "AKnownVec", 0L))
TRUE
})
## Mix
setClass("MixNormZero",
prototype = prototype(iMethodPrior = 31L,
slotsToExtract = c("prodVectorsMix",
"omegaVectorsMix",
"weightMix",
"componentWeightMix",
"omegaComponentWeightMix",
"levelComponentWeightMix",
"meanLevelComponentWeightMix",
"phiMix",
"omegaLevelComponentWeightMix",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", TRUE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Mix",
"NormMixin",
"ZeroMixin"))
setClass("MixNormCov",
prototype = prototype(iMethodPrior = 32L,
slotsToExtract = c("eta", "tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", TRUE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Mix",
"CovariatesMixin",
"NormMixin"))
setClass("MixRobustZero",
prototype = prototype(iMethodPrior = 33L,
slotsToExtract = "tau",
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", TRUE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Mix",
"RobustMixin",
"ZeroMixin"))
setClass("MixRobustCov",
prototype = prototype(iMethodPrior = 34L,
slotsToExtract = c("eta", "tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", TRUE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Mix",
"CovariatesMixin",
"RobustMixin"))
## Zero
setClass("Zero",
prototype = prototype(iMethodPrior = 40L,
slotsToExtract = character(),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", TRUE)),
contains = c("Prior",
"AllStrucZeroMixin"),
validity = function(object) {
isSaturated <- object@isSaturated@.Data
## is not saturated
if (isSaturated)
return(gettextf("prior has class \"%s\" but '%s' is %s",
"Zero", "isSaturated", "TRUE"))
TRUE
})
## DLMPredict, NoTrend
setClass("DLMNoTrendNormZeroNoSeasonPredict",
prototype = prototype(iMethodPrior = 105L),
contains = c("DLMNoTrendNormZeroNoSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendNormZeroWithSeasonPredict",
prototype = prototype(iMethodPrior = 106L),
contains = c("DLMNoTrendNormZeroWithSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendNormCovNoSeasonPredict",
prototype = prototype(iMethodPrior = 107L),
contains = c("DLMNoTrendNormCovNoSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendNormCovWithSeasonPredict",
prototype = prototype(iMethodPrior = 108L),
contains = c("DLMNoTrendNormCovWithSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendRobustZeroNoSeasonPredict",
prototype = prototype(iMethodPrior = 109L),
contains = c("DLMNoTrendRobustZeroNoSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendRobustZeroWithSeasonPredict",
prototype = prototype(iMethodPrior = 110L),
contains = c("DLMNoTrendRobustZeroWithSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendRobustCovNoSeasonPredict",
prototype = prototype(iMethodPrior = 111L),
contains = c("DLMNoTrendRobustCovNoSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendRobustCovWithSeasonPredict",
prototype = prototype(iMethodPrior = 112L),
contains = c("DLMNoTrendRobustCovWithSeason",
"DLMPredictMixin"))
## DLM, WithTrend
setClass("DLMWithTrendNormZeroNoSeasonPredict",
prototype = prototype(iMethodPrior = 113L),
contains = c("DLMWithTrendNormZeroNoSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendNormZeroWithSeasonPredict",
prototype = prototype(iMethodPrior = 114L),
contains = c("DLMWithTrendNormZeroWithSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendNormCovNoSeasonPredict",
prototype = prototype(iMethodPrior = 115L),
contains = c("DLMWithTrendNormCovNoSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendNormCovWithSeasonPredict",
prototype = prototype(iMethodPrior = 116L),
contains = c("DLMWithTrendNormCovWithSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendRobustZeroNoSeasonPredict",
prototype = prototype(iMethodPrior = 117L),
contains = c("DLMWithTrendRobustZeroNoSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendRobustZeroWithSeasonPredict",
prototype = prototype(iMethodPrior = 118L),
contains = c("DLMWithTrendRobustZeroWithSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendRobustCovNoSeasonPredict",
prototype = prototype(iMethodPrior = 119L),
contains = c("DLMWithTrendRobustCovNoSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendRobustCovWithSeasonPredict",
prototype = prototype(iMethodPrior = 120L),
contains = c("DLMWithTrendRobustCovWithSeason",
"DLMPredictMixin"))
## MixPredict
setClass("MixNormZeroPredict",
prototype = prototype(iMethodPrior = 131L),
contains = c("MixNormZero",
"MixPredictMixin"))
setClass("MixNormCovPredict",
prototype = prototype(iMethodPrior = 132L),
contains = c("MixNormCov",
"MixPredictMixin"))
setClass("MixRobustZeroPredict",
prototype = prototype(iMethodPrior = 133L),
contains = c("MixRobustZero",
"MixPredictMixin"))
setClass("MixRobustCovPredict",
prototype = prototype(iMethodPrior = 134L),
contains = c("MixRobustCov",
"MixPredictMixin"))
StatisticsNZ/demest documentation built on Nov. 2, 2023, 7:56 p.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
setClass("Prior",
contains = c("VIRTUAL",
"SlotsToExtract",
"IMethodPrior",
"ComponentFlagsMixin",
"IsSaturatedMixin",
"JMixin"))
setClass("Exch",
contains = c("VIRTUAL",
"Prior",
"AllStrucZeroMixin"))
setClass("DLM",
contains = c("VIRTUAL",
"Prior",
"AAlphaMixin",
"AllStrucZeroMixin",
"AlongAllStrucZeroMixin",
"AlphaDLMMixin",
"IAlongMixin",
"IteratorStateMixin",
"IteratorVMixin",
"KLMixin",
"NuAlphaMixin",
"OmegaAlphaMixin",
"OmegaAlphaMaxMixin",
"PhiMixin",
"PhiKnownMixin",
"PhiMinMaxMixin",
"Shape1Shape2PhiMixin"))
setClass("ICAR",
contains = c("VIRTUAL",
"Prior",
"AlphaICARMixin"))
setClass("Known",
contains = c("VIRTUAL",
"Prior",
"AllStrucZeroMixin",
"AlphaKnownMixin",
"AlphaKnownAllMixin",
"MetadataAllMixin"),
validity = function(object) {
alphaKnown <- object@alphaKnown@.Data
J <- object@J@.Data
isSaturated <- object@isSaturated@.Data
allStrucZero <- object@allStrucZero
## 'alphaKnown' has length 'J'
if (!identical(length(alphaKnown), J))
return(gettextf("'%s' does not have length '%s'",
"alphaKnown", "J"))
## is not saturated
if (isSaturated)
return(gettextf("prior has class \"%s\" but '%s' is %s",
"Known", "isSaturated", "TRUE"))
## 'alphaKnown' is zero if 'allStrucZero' is TRUE
if (any(allStrucZero & (alphaKnown != 0)))
return(gettextf("elements where '%s' is %s but '%s' does not equal %d",
"allStrucZero", "TRUE", "alphaKnown", 0L))
TRUE
})
setClass("Mix",
contains = c("VIRTUAL",
"Prior",
"AComponentWeightMixMixin",
"ALevelComponentWeightMixMixin",
"aMixMixin",
"AVectorsMixMixin",
"AllStrucZeroMixin",
"AlphaMixMixin",
"CMixMixin",
"ComponentWeightMixMixin",
"DimBetaMixin",
"IAlongMixin",
"FoundIndexClassMaxPossibleMixMixin",
"IndexClassMaxMixMixin",
"IndexClassMaxPossibleMixMixin",
"IndexClassMaxUsedMixMixin",
"IndexClassMixMixin",
"IndexClassProbMixMixin",
"IteratorProdVectorMix",
"IteratorsDimsMixMixin",
"LatentWeightMixMixin",
"LatentComponentWeightMixMixin",
"LevelComponentWeightMinMaxMixin",
"LevelComponentWeightMixMixin",
"mMixMixin",
"MeanLevelComponentWeightMixMixin",
"NuComponentWeightMixMixin",
"NuLevelComponentWeightMixMixin",
"NuVectorsMixMixin",
"OmegaComponentWeightMaxMixMixin",
"OmegaComponentWeightMixMixin",
"OmegaLevelComponentWeightMaxMixMixin",
"OmegaLevelComponentWeightMixMixin",
"OmegaVectorsMaxMixMixin",
"OmegaVectorsMixMixin",
"PhiKnownMixin",
"PhiMinMaxMixin",
"PhiMixMixin",
"PosProdVectorsMixMixin",
"PriorMeanLevelComponentWeightMixMixin",
"PriorSDLevelComponentWeightMixMixin",
"ProdVectorsMixMixin",
"RMixMixin",
"Shape1Shape2PhiMixin",
"SumsWeightsMixMixin",
"ToleranceMixin",
"VectorsMixMixin",
"WeightMixMixin",
"YXXXMixMixin"),
validity = function(object) {
## at least 2 dimensions
TRUE
})
## TimeInvariant
setClass("TimeInvariant",
prototype = prototype(iMethodPrior = -1L,
slotsToExtract = character(),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", TRUE),
isSaturated = methods::new("LogicalFlag", FALSE)),
contains = "Prior",
validity = function(object) {
isSaturated <- object@isSaturated@.Data
## is not saturated
if (isSaturated)
return(gettextf("prior has class \"%s\" but '%s' is %s",
"TimeInvariant", "isSaturated", "TRUE"))
TRUE
})
## ExchFixed
setClass("ExchFixed",
prototype = prototype(iMethodPrior = 0L,
slotsToExtract = character(),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", TRUE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
J = methods::new("Length", 1L),
mean = methods::new("Parameter", 0),
tau = methods::new("Scale", 1)),
contains = c("Prior",
"AllStrucZeroMixin",
"MeanMixin",
"TauMixin"),
validity = function(object) {
isSaturated <- object@isSaturated@.Data
## is not saturated
if (isSaturated)
return(gettextf("prior has class \"%s\" but '%s' is %s",
"Known", "isSaturated", "TRUE"))
TRUE
})
setClassUnion("Exchangeable",
members = c("Exch", "ExchFixed"))
## Exch
setClass("ExchNormZero",
prototype = prototype(iMethodPrior = 1L,
slotsToExtract = "tau",
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Exch",
"NormMixin",
"ZeroMixin"))
setClass("ExchNormCov",
prototype = prototype(iMethodPrior = 2L,
slotsToExtract = c("eta", "tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Exch",
"CovariatesMixin",
"NormMixin"))
setClass("ExchRobustZero",
prototype = prototype(iMethodPrior = 3L,
slotsToExtract = "tau",
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Exch",
"RobustMixin",
"ZeroMixin"))
setClass("ExchRobustCov",
prototype = prototype(iMethodPrior = 4L,
slotsToExtract = c("eta", "tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Exch",
"CovariatesMixin",
"RobustMixin"))
## DLM, NoTrend
setClass("DLMNoTrendNormZeroNoSeason",
prototype = prototype(iMethodPrior = 5L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"NormMixin",
"NoTrendMixin",
"ZeroMixin"))
setClass("DLMNoTrendNormZeroWithSeason",
prototype = prototype(iMethodPrior = 6L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"s",
"omegaSeason",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"NormMixin",
"NoTrendMixin",
"SeasonMixin",
"ZeroMixin"))
setClass("DLMNoTrendNormCovNoSeason",
prototype = prototype(iMethodPrior = 7L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"CovariatesMixin",
"NormMixin",
"NoTrendMixin"))
setClass("DLMNoTrendNormCovWithSeason",
prototype = prototype(iMethodPrior = 8L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"s",
"omegaSeason",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"CovariatesMixin",
"NormMixin",
"NoTrendMixin",
"SeasonMixin"))
setClass("DLMNoTrendRobustZeroNoSeason",
prototype = prototype(iMethodPrior = 9L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"NoTrendMixin",
"RobustMixin",
"ZeroMixin"))
setClass("DLMNoTrendRobustZeroWithSeason",
prototype = prototype(iMethodPrior = 10L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"s",
"omegaSeason",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"NoTrendMixin",
"RobustMixin",
"SeasonMixin",
"ZeroMixin"))
setClass("DLMNoTrendRobustCovNoSeason",
prototype = prototype(iMethodPrior = 11L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"CovariatesMixin",
"NoTrendMixin",
"RobustMixin"))
setClass("DLMNoTrendRobustCovWithSeason",
prototype = prototype(iMethodPrior = 12L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"phi",
"s",
"omegaSeason",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7)),
contains = c("DLM",
"CovariatesMixin",
"NoTrendMixin",
"RobustMixin",
"SeasonMixin"))
## DLM, WithTrend
setClass("DLMWithTrendNormZeroNoSeason",
prototype = prototype(iMethodPrior = 13L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89),
nrow = 2L,
ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89),
nrow = 2L,
ncol = 2L))),
contains = c("DLM",
"NormMixin",
"WithTrendMixin",
"ZeroMixin"))
setClass("DLMWithTrendNormZeroWithSeason",
prototype = prototype(iMethodPrior = 14L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"s",
"omegaSeason",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"NormMixin",
"SeasonMixin",
"WithTrendMixin",
"ZeroMixin"))
setClass("DLMWithTrendNormCovNoSeason",
prototype = prototype(iMethodPrior = 15L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"CovariatesMixin",
"NormMixin",
"WithTrendMixin"))
setClass("DLMWithTrendNormCovWithSeason",
prototype = prototype(iMethodPrior = 16L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"s",
"omegaSeason",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"CovariatesMixin",
"NormMixin",
"SeasonMixin",
"WithTrendMixin"))
setClass("DLMWithTrendRobustZeroNoSeason",
prototype = prototype(iMethodPrior = 17L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"RobustMixin",
"WithTrendMixin",
"ZeroMixin"))
setClass("DLMWithTrendRobustZeroWithSeason",
prototype = prototype(iMethodPrior = 18L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"s",
"omegaSeason",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"RobustMixin",
"SeasonMixin",
"WithTrendMixin",
"ZeroMixin"))
setClass("DLMWithTrendRobustCovNoSeason",
prototype = prototype(iMethodPrior = 19L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
meanDelta = methods::new("Parameter", 0),
AAlpha = methods::new("Scale", 1),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"CovariatesMixin",
"RobustMixin",
"WithTrendMixin"))
setClass("DLMWithTrendRobustCovWithSeason",
prototype = prototype(iMethodPrior = 20L,
slotsToExtract = c("alphaDLM",
"omegaAlpha",
"deltaDLM",
"omegaDelta",
"phi",
"s",
"omegaSeason",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", TRUE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", TRUE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
AAlpha = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuAlpha = methods::new("DegreesFreedom", 7),
omegaAlpha = methods::new("Scale", 1),
ADelta = methods::new("Scale", 1),
ADelta0 = methods::new("Scale", 1),
meanDelta = methods::new("Parameter", 0),
nuDelta = methods::new("DegreesFreedom", 7),
omegaDelta = methods::new("Scale", 1),
phi = 0.89,
phiKnown = methods::new("LogicalFlag", FALSE),
minPhi = 0.8,
maxPhi = 0.98,
shape1Phi = methods::new("Scale", 2),
shape2Phi = methods::new("Scale", 2),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7),
omegaSeason = methods::new("Scale", 1),
ASeason = methods::new("Scale", 1),
nuSeason = methods::new("DegreesFreedom", 7),
GWithTrend = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L)),
WSqrt = methods::new("NumericMatrixSquare", diag(2L)),
WSqrtInvG = methods::new("NumericMatrixSquare",
matrix(c(1, 0, 1, 0.89), nrow = 2L, ncol = 2L))),
contains = c("DLM",
"CovariatesMixin",
"RobustMixin",
"SeasonMixin",
"WithTrendMixin"))
## ICAR
setClass("ICARNormZero",
prototype = prototype(iMethodPrior = 21L,
slotsToExtract = c("alphaICAR",
"omegaAlpha",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", TRUE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("ICAR",
"NormMixin",
"ZeroMixin"))
setClass("ICARNormCov",
prototype = prototype(iMethodPrior = 22L,
slotsToExtract = c("alphaICAR",
"omegaAlpha",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", TRUE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("ICAR",
"CovariatesMixin",
"NormMixin"))
setClass("ICARRobustZero",
prototype = prototype(iMethodPrior = 23L,
slotsToExtract = c("alphaICAR",
"omegaAlpha",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", TRUE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("ICAR",
"RobustMixin",
"ZeroMixin"))
setClass("ICARRobustCov",
prototype = prototype(iMethodPrior = 24L,
slotsToExtract = c("alphaICAR",
"omegaAlpha",
"eta",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", TRUE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("ICAR",
"CovariatesMixin",
"RobustMixin"))
## Known
setClass("KnownCertain",
prototype = prototype(iMethodPrior = 29L,
slotsToExtract = character(),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", TRUE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", TRUE)),
contains = "Known")
setClass("KnownUncertain",
prototype = prototype(iMethodPrior = 30L,
slotsToExtract = character(),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", TRUE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", TRUE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE)),
contains = c("Known",
"AKnownVecMixin",
"AKnownAllVecMixin"),
validity = function(object) {
AKnownVec <- object@AKnownVec
J <- object@J@.Data
allStrucZero <- object@allStrucZero
## 'AKnownVec' has length 'J'
if (!identical(length(AKnownVec), J))
return(gettextf("'%s' does not have length '%s'",
"AKnownVec", "J"))
## 'AKnownVec' is zero if 'allStrucZero' is TRUE
if (any(allStrucZero & (AKnownVec != 0)))
return(gettextf("elements where '%s' is %s but '%s' does not equal %d",
"allStrucZero", "TRUE", "AKnownVec", 0L))
TRUE
})
## Mix
setClass("MixNormZero",
prototype = prototype(iMethodPrior = 31L,
slotsToExtract = c("prodVectorsMix",
"omegaVectorsMix",
"weightMix",
"componentWeightMix",
"omegaComponentWeightMix",
"levelComponentWeightMix",
"meanLevelComponentWeightMix",
"phiMix",
"omegaLevelComponentWeightMix",
"tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", TRUE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Mix",
"NormMixin",
"ZeroMixin"))
setClass("MixNormCov",
prototype = prototype(iMethodPrior = 32L,
slotsToExtract = c("eta", "tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", TRUE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", TRUE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", FALSE),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Mix",
"CovariatesMixin",
"NormMixin"))
setClass("MixRobustZero",
prototype = prototype(iMethodPrior = 33L,
slotsToExtract = "tau",
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", TRUE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Mix",
"RobustMixin",
"ZeroMixin"))
setClass("MixRobustCov",
prototype = prototype(iMethodPrior = 34L,
slotsToExtract = c("eta", "tau"),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", TRUE),
hasCovariates = methods::new("LogicalFlag", TRUE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", TRUE),
isZeroVar = methods::new("LogicalFlag", FALSE),
nuBeta = methods::new("DegreesFreedom", 4),
AEtaIntercept = methods::new("Scale", 10),
tau = methods::new("Scale", 1),
ATau = methods::new("Scale", 1),
nuTau = methods::new("DegreesFreedom", 7)),
contains = c("Mix",
"CovariatesMixin",
"RobustMixin"))
## Zero
setClass("Zero",
prototype = prototype(iMethodPrior = 40L,
slotsToExtract = character(),
hasAlphaDLM = methods::new("LogicalFlag", FALSE),
hasAlphaICAR = methods::new("LogicalFlag", FALSE),
hasAlphaMix = methods:::new("LogicalFlag", FALSE),
hasCovariates = methods::new("LogicalFlag", FALSE),
hasAlphaKnown = methods::new("LogicalFlag", FALSE),
hasMean = methods::new("LogicalFlag", FALSE),
hasSeason = methods::new("LogicalFlag", FALSE),
isKnownUncertain = methods::new("LogicalFlag", FALSE),
isNorm = methods::new("LogicalFlag", FALSE),
isRobust = methods::new("LogicalFlag", FALSE),
isZeroVar = methods::new("LogicalFlag", TRUE)),
contains = c("Prior",
"AllStrucZeroMixin"),
validity = function(object) {
isSaturated <- object@isSaturated@.Data
## is not saturated
if (isSaturated)
return(gettextf("prior has class \"%s\" but '%s' is %s",
"Zero", "isSaturated", "TRUE"))
TRUE
})
## DLMPredict, NoTrend
setClass("DLMNoTrendNormZeroNoSeasonPredict",
prototype = prototype(iMethodPrior = 105L),
contains = c("DLMNoTrendNormZeroNoSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendNormZeroWithSeasonPredict",
prototype = prototype(iMethodPrior = 106L),
contains = c("DLMNoTrendNormZeroWithSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendNormCovNoSeasonPredict",
prototype = prototype(iMethodPrior = 107L),
contains = c("DLMNoTrendNormCovNoSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendNormCovWithSeasonPredict",
prototype = prototype(iMethodPrior = 108L),
contains = c("DLMNoTrendNormCovWithSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendRobustZeroNoSeasonPredict",
prototype = prototype(iMethodPrior = 109L),
contains = c("DLMNoTrendRobustZeroNoSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendRobustZeroWithSeasonPredict",
prototype = prototype(iMethodPrior = 110L),
contains = c("DLMNoTrendRobustZeroWithSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendRobustCovNoSeasonPredict",
prototype = prototype(iMethodPrior = 111L),
contains = c("DLMNoTrendRobustCovNoSeason",
"DLMPredictMixin"))
setClass("DLMNoTrendRobustCovWithSeasonPredict",
prototype = prototype(iMethodPrior = 112L),
contains = c("DLMNoTrendRobustCovWithSeason",
"DLMPredictMixin"))
## DLM, WithTrend
setClass("DLMWithTrendNormZeroNoSeasonPredict",
prototype = prototype(iMethodPrior = 113L),
contains = c("DLMWithTrendNormZeroNoSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendNormZeroWithSeasonPredict",
prototype = prototype(iMethodPrior = 114L),
contains = c("DLMWithTrendNormZeroWithSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendNormCovNoSeasonPredict",
prototype = prototype(iMethodPrior = 115L),
contains = c("DLMWithTrendNormCovNoSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendNormCovWithSeasonPredict",
prototype = prototype(iMethodPrior = 116L),
contains = c("DLMWithTrendNormCovWithSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendRobustZeroNoSeasonPredict",
prototype = prototype(iMethodPrior = 117L),
contains = c("DLMWithTrendRobustZeroNoSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendRobustZeroWithSeasonPredict",
prototype = prototype(iMethodPrior = 118L),
contains = c("DLMWithTrendRobustZeroWithSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendRobustCovNoSeasonPredict",
prototype = prototype(iMethodPrior = 119L),
contains = c("DLMWithTrendRobustCovNoSeason",
"DLMPredictMixin"))
setClass("DLMWithTrendRobustCovWithSeasonPredict",
prototype = prototype(iMethodPrior = 120L),
contains = c("DLMWithTrendRobustCovWithSeason",
"DLMPredictMixin"))
## MixPredict
setClass("MixNormZeroPredict",
prototype = prototype(iMethodPrior = 131L),
contains = c("MixNormZero",
"MixPredictMixin"))
setClass("MixNormCovPredict",
prototype = prototype(iMethodPrior = 132L),
contains = c("MixNormCov",
"MixPredictMixin"))
setClass("MixRobustZeroPredict",
prototype = prototype(iMethodPrior = 133L),
contains = c("MixRobustZero",
"MixPredictMixin"))
setClass("MixRobustCovPredict",
prototype = prototype(iMethodPrior = 134L),
contains = c("MixRobustCov",
"MixPredictMixin"))
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.