MEA_L20

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

#

# MEA_L20 (Late 20th) Model (Middle-East Africa)

#

# Measurement Matrix (Growth) (N-CO2-EG-Q) (Q-EG)

#     EN.ATM.CO2E.KT EG.USE.COMM.KT.OE NY.GDP.MKTP.KD SL.TLF.TOTL.IN SP.POP.TOTL SL.UEM.TOTL.ZS

#[1,]         0.4140             0.409          0.413         0.4163      0.4163         0.3800

#[2,]        -0.2320            -0.361         -0.216        -0.0443      0.0458         0.8746

#[3,]         0.0599            -0.604          0.708         0.1760     -0.3125        -0.0336

#

# Fraction of Variance 

#[1] 0.959 0.996 0.999 0.999 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(1.013898777,  0.013960359,  0.014314423,  0.160971128,

                    -0.035391585,  1.097936826, -0.004866923, -0.023976869,

                    -0.003813121, -0.009715855,  0.919184163 , 0.005569086,

                     0.000000000, 0.000000000,  0.000000000,  1.000000000

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

#

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

# f[1,1] <- 0.926214020

# f[2,2] <- 0.90     # f[2,2] <- 1.002984227 Stability isn't enough

# f[3,3] <- 0.839690586

#

h <- eye(3,4)

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

MEA <- SS(F=f,H=h,K=k,z0=c(0.32392455, -0.05602608,  0.01030725,  1.0000000000),

              output.names=c("MEA1","MEA2","MEA3"))

print(MEA)

is.SS(MEA)

stability(MEA)

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

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

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

tfplot(MEA.f)

AIC(m)

shockDecomposition(m)