Man pages for StatisticsNZ/demest
Bayesian Demographic Estimation and Forecasting

AggregateSpecify aggregate values.
ComponentsSpecify priors for the components in a Mix prior.
Components-classAn S4 class to specify the components of a Mix prior.
continueEstimationAdd extra iterations to burnin or output.
CovariatesSpecify covariates in a prior for a main effect or...
Covariates-classS4 class to specify the covariates term of a prior.
DampSpecify the amount of damping in a DLM prior.
Damp-classS4 classes to specify damping terms in DLM priors.
demest-packageBayesian demographic estimation and forecasting.
DLMSpecify a Dynamic Linear Model (DLM) prior.
equivalentSampleConvert estimates from a complex survey into a form suitable...
ErrorSpecify the error term in a prior for a main effect or...
Error-classS4 classes to specify error terms for priors.
estimateAccountEstimate demographic account and models from multiple noisy...
estimateCountsEstimate counts and model from multiple noisy datasets.
estimateModelEstimate model from single reliable dataset.
ExchSpecify an exchangeable prior.
ExchFixedSpecify a simple exchangeable prior.
fetchExtract estimates from model output.
fetchBothExtract combined results from estimation and prediction.
fetchFiniteSDFinite-population standard deviations.
fetchMCMCCreate a list of objects for analysis with package "coda".
fetchSummarySummarise estimation output.
FiniteSD-classS4 class to hold finite-population standard deviations.
finiteYEstimate or predict finite-population quantity 'y'.
gelmanDiagObtain potential scale reduction factors (Rhats).
HalfTSpecify a half-t distribution.
HalfT-classAn S4 class to specify a truncated half-_t_ distribution.
halft-distnThe half-t distribution.
InitialSpecify the prior for the initial value of the trend term in...
Initial-classAn S4 class to specify a normal prior for a scalar parameter.
KnownSpecify a prior where the mean varies but is treated as...
LevelSpecify the level term in a DLM prior.
Level-classAn S4 class to specify the level term in a DLM prior.
likelihoodSpecify first two levels of hierarchical model.
listContentsList of output from estimate function.
metropolisExtract information on Metropolis-Hastings updates.
MixSpecify a Mix prior.
ModelSpecify a model for a single demographic series or dataset.
NormSpecify a normal distribution centered at 0.
NormalFixedSpecify a model based on a normal distribution with known...
Norm-classAn S4 class to specify a normal distribution.
parametersExtract summaries of parameter estimates from a...
plotHalfTPlot the half-t distribution.
PoissonBinomialSpecify a model based on a Poisson-binomial mixture.
predictAccountUse results from function estimateAccount to make...
predictCountsUse results from function estimateCounts to make predictions.
predictModelUse results from function estimateModel to make predictions.
SeasonSpecify a seasonal effect in a DLM prior.
Season-classAn S4 class to specify a seasonal effect in a DLM prior.
show-methodsPrint description of model or prior.
showModelShow final model specification.
SpecAggregate-classS4 classes to represent aggregate values.
SpecDLM-classAn S4 class to specify a dynamic linear model (DLM) prior.
SpecExch-classA S4 class to specify an exchangeable prior.
SpecExchFixed-classA S4 class to specify a simple exchangeable prior.
SpecKnown-classA S4 class to specify a Known prior.
SpecLikelihood-classS4 classes to specify one or two levels of a model.
SpecMix-classAn S4 class to specify a Mix prior.
SpecModel-classS4 classes to specify a model.
SpecPrior-classA S4 superclass for prior specifications.
SpecZero-classAn S4 class to specify a Zero prior.
SummaryResults-classS4 class summarizing results from estimation or prediction.
TrendSpecify the trend term in a DLM prior.
Trend-classAn S4 class to specify the trend term in a DLM prior.
WeightsSpecify priors for the weights in a Mix prior.
Weights-classAn object of class 'Weights' is used to specify the trend...
ZeroSpecify a prior that sets all terms to zero.
StatisticsNZ/demest documentation built on Nov. 8, 2017, 12:01 a.m.