BE_LM Model

# Cut-and-Paste Code Below into Window Above and RUN

#

# BE_LM (Late Modern) Model (Belgium)

#

# Measurement Matrix 

#            Q      N        U  HOURS  XREAL      X     L

#[1,] 0.390585  0.379  0.39054 -0.386  0.385  0.364 0.348

#[2,] 0.000242  0.365 -0.00413  0.220 -0.242 -0.540 0.685

#[3,] 0.162385 -0.196 -0.33818  0.652  0.322  0.420 0.338

#

# Fraction of Variance 

#[1] 0.936 1.000 1.000 1.000 1.000 1.000 1.000

#

merge.forecast <- function (fx,n=1) {

x <- splice(fx$pred,fx$forecast[[n]])

colnames(x) <- seriesNames(fx$data$output)

return(x)

}

AIC <- function(model) {informationTestsCalculations(model)[3]}

require(dse)

require(matlab)

f <- matrix( c(1.001134557, 0.01309593, -0.1332430,  0.171537934,

                     -0.034347955, 1.01510230, -0.4299705, -0.008530308,

                        0.001554447, 0.01517904,  0.8659064, -0.004688827,

0.00000000,  0.0000000,  0.0000000,  1.0000000000

),byrow=TRUE,nrow=4,ncol=4)

#

# To stabilize the model, uncomment the next three lines:

# f[1,1] <- 0.991123212;f[2,2] <- 1.00495128; f[3,3] <-  0.8572473

#

h <- eye(3,4)

k <- (f[,1:3,drop=FALSE])

BE_LM <- SS(F=f,H=h,K=k,z0=c(0.343783528, -0.021065363, -0.008611747,  1.0000000000),

              output.names=c("BE1","BE2","BE3"))

print(BE_LM)

is.SS(BE_LM)

#  stability(SS(F=F[1:3,1:3,drop=FALSE],H=eye(3),R=eye(3),Q=eye(3))

stability(BE_LM)

BE_LM.data <- (simulate(BE_LM,sampleT=100,start=1950))

BE_LM.data <- simulate(BE_LM,sampleT=20,noise=matrix(0,20,3),start=1950)

BE_LM.f <- forecast(m <- l(BE_LM,BE_LM.data),horizon=150)

tfplot(BE_LM.f)

AIC(m)

shockDecomposition(m)