dlm.retro {DGM}R Documentation

Calculate the location and scale parameters for the time-varying coefficients given all the observations. West, M. & Harrison, J., 1997. Bayesian Forecasting and Dynamic Models. Springer New York.

Description

Calculate the location and scale parameters for the time-varying coefficients given all the observations. West, M. & Harrison, J., 1997. Bayesian Forecasting and Dynamic Models. Springer New York.

Usage

dlm.retro(mt, CSt, RSt, nt, dt)

Arguments

mt

the vector or matrix of the posterior mean (location parameter), dim = p x T, where p is the number of thetas (at any time t) and T is the number of time points

CSt

the posterior scale matrix with dim = p x p x T (unscaled by the observation variance)

RSt

the prior scale matrix with dim = p x p x T (unscaled by the observation variance)

nt

vector of the updated hyperparameters for the precision phi with length T

dt

vector of the updated hyperparameters for the precision phi with length T

Value

smt = the location parameter of the retrospective distribution with dimension p x T sCt = the scale matrix of the retrospective distribution with dimension p x p x T


[Package DGM version 1.7.4 Index]