IN_LM Model

# Cut-and-Paste Code below into Window Above and Run

#

# IN_LM India 1950-2000+  (IN)

#

# Measurement Matrix 

#         Q      N

#[1,] 0.707  0.707

#[2,] 0.707 -0.707

#

# Fraction of Variance 

#[1] 0.992 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( 1.02900365, -0.1043974,  0.0940567465,

                       0.01197189,  0.9807005, -0.0006520039,

                        0.000000000,  0.00000000, 1.0000000000)

                        ,byrow=TRUE,nrow=3,ncol=3)

#

# To stabilize the System, Uncomment following line

# f[1,1] <- 0.98

h <- eye(2,3)

k <- (f[,1:2,drop=FALSE])

IN_LM <- SS(F=f,H=h,K=k,z0=c(0.0940567465, -0.0006520039,  1.0000000000),

              output.names=c("IN1","IN2"))

print(IN_LM)

is.SS(IN_LM)

stability(IN_LM)

tfplot(IN_LM.data <- simulate(IN_LM,sampleT=150,start=0))

#IN_LM.data <- simulate(IN_LM,sampleT=20,noise=matrix(0,20,2))

IN_LM.f <- forecast(m <- l(IN_LM,IN_LM.data),horizon=50)

tfplot(IN_LM.f)

AIC(m)

shockDecomposition(toSSChol(m))