Leibenstein Expanded Model

#

# Leibenstein Expanded Model (Cut an paste code in window above and Run (Cmd-Enter)

#

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

require(dse)

require(matlab)

f <- matrix( c(0.68794694, -0.23702406, -0.3702652,    0,    0,  0.15804543,

                     0.14468969,   0.98257831,  0.1110937,    0,    0, -0.25296643,

                    -0.04495851, -0.03512983,  1.0971569,    0,    0,  0.03045473,

                    -0.14468969, -0.98257831, -0.1110937,    0,    0,  0.25296643,

                    -0.68794694,  0.23702406,  0.3702652,    0,    0, -0.15804543,

                     0.00000000,  0.00000000,  0.0000000,    0,    0,  1.00000000

),byrow=TRUE,nrow=6,ncol=6)

h <- eye(5,6)

k <- (f[,1:5,drop=FALSE])

LMx <- SS(F=f,H=h,K=k,z0=c( 0.15804543, -0.25296643,  0.03045473,  0.25296643, -0.15804543,1),

              output.names=c("I","II","III","V","-I"))

print(LMx)

is.SS(LMx)

stability(LMx)

n <- 20

LMx.data <- simulate(LMx,sampleT=n,noise=matrix(0,n,5),start=1)

LMx.data2 <- simulate(LMx,sampleT=n,start=1)

tfplot(LMx.data)

AIC(l(LMx,LMx.data))

tfplot(LMx.data2)

AIC(l(LMx,LMx.data2))