SSM-class: SSM class

In jrnold/yakf: Yet another Kalman Filter package

Description

The "SSM" class represents a dynamic linear model, also called state-space model.

Usage

  SSM(T, Z, H, Q, R = NULL, a1 = NULL, P1 = NULL,
    cc = NULL, dd = NULL, kappa = 1e+07)

Arguments

T	Matrix of dimension m x m.
Z	Matrix of dimension p x m.
H	Matrix of dimension m x m.
R	Matrix of dimension p x r.
Q	Matrix of dimension r x r.
P1	Matrix of dimension m x m. If NULL, then a diffuse diagonal Matrix is used. The diagonal of this Matrix is set to 10^6 times the maximum of 1 or values along the diagonal of HH and GG.
a1	Matrix of length m. If NULL, then set to a 0 vector.
dd	Matrix of dimension N. If NULL, then set to a 0 vector.
cc	Matrix of dimension m. If NULL, then set to a 0 vector.
kappa	Default multiplier for diagonal values of P1, if P1 = NULL.

Value

An object of class SSM.

Slots

T

"MatrixOrMatrixList". The T matrix.

Z

"MatrixOrMatrixList". The Z matrix.

H

"MatrixOrMatrixList". The H matrix.

Q

"MatrixOrMatrixList". The Q matrix.

R

"MatrixOrMatrixList". The R matrix.

P1

"MatrixOrMatrixList". The P_1 matrix with the covariance of the initial states.

a1

"MatrixOrMatrixList". The a_1 vector with the mean of initial states.

dd

"MatrixOrMatrixList". The d vector.

cc

"MatrixOrMatrixList". The c vector.

Details

The structure and notation of state spece models represented this class is based on that used in SsfPack and dlm. See the package vignette for details.

References

Giovanni Petris (2010), An R Package for Dynamic Linear Models.

Petris, Petrone, and Campagnoli, Dynamic Linear Models with R, Springer (2009).

West and Harrison, Bayesian forecasting and dynamic models (2nd ed.), Springer (1997).

See Also

SSM

jrnold/yakf documentation built on May 20, 2019, 2:06 a.m.