ECC Leibenstein Model

#

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

#

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

require(dse)

require(matlab)

# Measurement Matrix 

#         I     II    III     IV      -I

#[1,] 0.390 -0.552  0.293  0.552 -0.390

#[2,] 0.522  0.208 -0.608 -0.208 -0.522

#[3,] 0.274  0.390  0.738 -0.390 -0.274

#

# Fraction of Variance 

#[1] 0.599 0.998 1.000 1.000 1.000#

f <- matrix( c( 0.85607762, -0.02092552, -0.3234873,  0.274825740,

                     -0.20393218,  1.13860151, -0.6416047, -0.105147205,

                      0.01733743 , 0.01928882,  0.7730030, -0.009853891,

                      0.00000000,  0.00000000,  0.0000000,  1.000000000

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

h <- eye(3,4)

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

LMc <- SS(F=f,H=h,K=k,z0=c( 0.274825740, -0.105147205, -0.009853891,  1.000000000),

              output.names=c("LM1","LM2","LM3"))

print(LMc)

is.SS(LMc)

stability(LMc)

n <- 20

LMc.data <- simulate(LMc,sampleT=n,noise=matrix(0,n,3),start=1)

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

tfplot(LMc.data)

AIC(l(LMc,LMc.data))

tfplot(LMc.data2)

AIC(l(LMc,LMc.data2))

shockDecomposition(toSSChol(LMc))