fpec {timsac}R Documentation

AR model Fitting for Control

Description

Perform AR model fitting for control.

Usage

  fpec(y, max.order=NULL, ncon=NULL, nman=0, inw=NULL)

Arguments

y a multivariate time series.
max.order upper limit of model order. Default is 2*sqrt(n), where n is the length of time series y.
ncon number of controlled variables. Default is d, where d is the dimension of the time series y.
nman number of maninpulated variables.
inw indicator; inw[i] (i=1,...,ncon) indicate the controlled variables and
inw[i+ncon] (i=1,...,nman) indicate the manipulate variables.

Value

cov covariance matrix rearrangement by inw.
fpec FPEC (AR model fitting for control).
rfpec RFPEC.
aic AIC.
ordermin order of minimum FPEC.
fpecmin minimum FPEC.
rfpecmin minimum RFPEC.
aicmin minimum AIC.
perr prediction error covariance matrix.
arcoef a set of coefficient matrices. arcoef[i,j,k] shows the value of i-th row, j-th column, k-th order.

References

H.Akaike and T.Nakagawa (1988) Statistical Analysis and Control of Dynamic Systems. Kluwer Academic publishers.

Examples

  ar <- array(0,dim=c(3,3,2))
  ar[,,1] <- matrix(c(0.4,  0,   0.3,
                      0.2, -0.1, -0.5,
                      0.3,  0.1, 0),3,3,byrow=TRUE)
  ar[,,2] <- matrix(c(0,  -0.3,  0.5,
                      0.7, -0.4,  1,
                      0,   -0.5,  0.3),3,3,byrow=TRUE)
  x <- matrix(rnorm(200*3),200,3)
  y <- mfilter(x,ar,"recursive")
  fpec(y, max.order=10, ncon=3, nman=0)

[Package timsac version 1.2.1 Index]