armax: Estimate ARMAX Models

In sysid: System Identification in R

Description

Fit an ARMAX model of the specified order given the input-output data

Usage

armax(x, order = c(0, 1, 1, 0), init_sys = NULL, intNoise = FALSE,
  options = optimOptions())

Arguments

x	an object of class idframe
order	Specification of the orders: the four integer components (na,nb,nc,nk) are the order of polynolnomial A, order of polynomial B + 1, order of the polynomial C,and the input-output delay respectively
init_sys	Linear polynomial model that configures the initial parameterization. Must be an ARMAX model. Overrules the order argument
intNoise	Logical variable indicating whether to add integrators in the noise channel (Default=FALSE)
options	Estimation Options, setup using optimOptions

Details

SISO ARMAX models are of the form

y[k] + a_1 y[k-1] + … + a_{na} y[k-na] = b_{nk} u[k-nk] + … + b_{nk+nb} u[k-nk-nb] + c_{1} e[k-1] + … c_{nc} e[k-nc] + e[k]

The function estimates the coefficients using non-linear least squares (Levenberg-Marquardt Algorithm)
The data is expected to have no offsets or trends. They can be removed using the detrend function.

Value

An object of class estpoly containing the following elements:

sys	an idpoly object containing the fitted ARMAX coefficients
fitted.values	the predicted response
residuals	the residuals
input	the input data used
call	the matched call
stats	A list containing the following fields: vcov - the covariance matrix of the fitted coefficients sigma - the standard deviation of the innovations
options	Option set used for estimation. If no custom options were configured, this is a set of default options
termination	Termination conditions for the iterative search used for prediction error minimization: WhyStop - Reason for termination iter - Number of Iterations iter - Number of Function Evaluations

References

Arun K. Tangirala (2015), Principles of System Identification: Theory and Practice, CRC Press, Boca Raton. Sections 14.4.1, 21.6.2

Examples

data(armaxsim)
z <- dataSlice(armaxsim,end=1533) # training set
mod_armax <- armax(z,c(1,2,1,2))
mod_armax

sysid documentation built on May 2, 2019, 4:18 a.m.