SpecDLM-class: An S4 class to specify a dynamic linear model (DLM) prior.

In StatisticsNZ/demest: Bayesian Demographic Estimation and Forecasting

An S4 class to specify a dynamic linear model (DLM) prior.

Description

An object of class SpecDLM specifies a prior in which elements that are next to each other are are expected to be more similar than elements that are distant for each other. DLMs are typically used to model variation over time, but are often also appropriate for variation over age.

Details

The prior consists of a level term, optional trend, seasonal, and covariates terms, and an error term. The error term can follow a normal or t distribution. For details, see the documentation for function DLM.

Slots

along

The name of the dimension that the time series (or age equivalents) extend along.

phi

Damping parameter.

phiKnown

Whether the damping parameter is known or is estimated from the data.

minPhi

Minimum value for the damping parameter.

maxPhi

Maximum value for the damping parameter.

nuAlpha

Degrees of freedom for the prior for the standard deviation for innovations in the level term.

AAlpha

Scale for the prior for the standard deviation for innovations in the level term.

omegaAlphaAMax

Maximum for the standard deviation for innovations in the level term.

nuDelta

Degrees of freedom for the prior for the standard deviation for innovations in the trend term.

ADelta

Scale for the prior for the standard deviation for innovations in the trend term.

omegaDeltaAMax

Maximum for the standard deviation for innovations in the trend term.

nSeason

Number of seasons.

nuSeason

Degrees of freedom for the prior for the standard deviation for innovations in the season term.

ASeason

Scale for the prior for the standard deviation for innovations in the season term.

omegaSeasonAMax

Maximum for the standard deviation for innovations in the season term.

formula

A formula with response mean.

data

A data.frame containing covariate data.

contrastsArg

A named list, the elements which are matrices or names of contrasts functions.

AIntercept

The standard deviation for the prior for the intercept in the covariates term.

nuEtaCoef

The degrees of freedom for the prior for the coefficients in the covariates term.

AEtaCoef

The scale for the prior for the coefficients in the covariates term.

nuBeta

The degrees of freedom for the error term, if the error term has a t distribution.

nuTau

The degrees of freedom for the truncated half-t prior for the standard deviation or scale parameter for the error term.

ATau

The scale for the truncated half-t prior for the standard deviation or scale parameter for the error term.

maxTau

The maximum value for the standard deviation or scale parameter for the error term.

shape1Phi

First 'sample size' parameter in beta prior for damping parameter.

shape2Phi

Second 'sample size' parameter in beta prior for damping parameter.

Warning

In normal usage, it should not be necessary to access, or even know about, the slots of a SpecDLM object. The slots are not part of the API of the package, and may change in future.

See Also

Object of class SpecDLM are generated using function DLM.

StatisticsNZ/demest documentation built on Nov. 2, 2023, 7:56 p.m.