SYL20 Model

#

# SYL20 BAU Model (cut and paste the following code into the window above and hit "Run (CMD-Enter)"

#

# Measurement Matrix    (Growth) (EF-EG)   (LU-KOF)

#

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

#[1,]          0.342            0.3239          0.341         0.3477

#[2,]         -0.112           -0.4920         -0.301        -0.0397

#[3,]         -0.142            0.0312         -0.192         0.0779

#     SP.POP.TOTL SL.UEM.TOTL.ZS    KOF      EF     HDI

#[1,]       0.346         0.3169  0.338  0.3053  0.3372

#[2,]      -0.176         0.0164  0.107  0.6926  0.3615

#[3,]      -0.130         0.8838 -0.363 -0.0417 -0.0684

#

# Fraction of Variance 

#

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

require(dse)

require(matlab)

f <- matrix( c(1.00000000,  0.000000000, 0.000000000,  0.0000000,

                       0.17863313 , 1.012095084, 0.009518299, -0.1063310,

                      -0.01364385, -0.030579490, 0.964634125,  0.1349448,

                      -0.01404508, -0.001345318, 0.046377182,  0.5953866

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

#

# To Stabilize, uncomment next line

#      f[2,2] <- 0.9

#

h <- matrix(c( 0,    1,    0,    0,

                0,    0,    1,    0,

                0,    0,    0,    1

),byrow=TRUE,nrow=3,ncol=4)

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

q <- matrix(c(0.00000000,  0.000000000,  0.000000000,

                      0.15175397, -0.006432653, -0.000383436,

                      0.08352866,  0.202360319,  0.013218201,

                      0.10689632, -0.055204665,  0.169694202

),byrow=TRUE,nrow=4,ncol=3)    

r <- matrix(c( 0.15248785,  0.0000000, 0.0000000,

                      0.07597308,  0.2165973, 0.0000000,

                      0.18955473, -0.1418127, 0.2850152

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

SYL20 <- SS(F=f,H=h,K=k,z0=c(  1.0000000, -4.0243179, -0.9160641 , 0.4561761),

              output.names=c("SY1","SY2","SY3"))

SYL20x <- SS(F=f,H=h,Q=q,R=r,z0=c( 1.0000000, -5.3541066, -0.7239263,  0.7703831),

              output.names=c("SY1","SY2","SY3"))

print(SYL20)

is.SS(SYL20)

stability(SYL20)

# tfplot(simulate(SYL20,sampleT=100))

SYL20.data <- simulate(SYL20,sampleT=50,noise=matrix(0,20,3))

SYL20.f <- forecast(l(SYL20,SYL20.data),horizon=50)

tfplot(SYL20.f)

AIC(l(SYL20,SYL20.data))

shockDecomposition(SYL20x)

#

#        Bootstrap Confidence Intervals

#           Keep counterfactuals within LCI-UCI for high probability

#

#           LCI Parameter       UCI P>=T[1] P< T[1] Std. Dev.      Bias   Bias-z

# [1,]  0.16225  0.178633  0.193228    0.58    0.42  0.015870 -0.005038  -0.3174

# [2,] -0.03742 -0.013644  0.005267    0.64    0.36  0.017066  0.188232  11.0297

# [3,] -0.04283 -0.014045  0.009960    0.48    0.52  0.024244  0.193590   7.9852

# [4,]  0.99583  1.012095  1.027692    0.31    0.69  0.012594 -0.828864 -65.8151

# [5,] -0.03843 -0.030579 -0.023407    0.58    0.42  0.006251  0.209250  33.4744

# [6,] -0.01400 -0.001345  0.008696    0.52    0.48  0.009112  0.179789  19.7321

# [7,] -0.05726  0.009518  0.075622    0.63    0.37  0.053955  0.152394   2.8245

# [8,]  0.90898  0.964634  1.003664    0.53    0.47  0.035058 -0.781779 -22.2998

# [9,]  0.00157  0.046377  0.084697    0.57    0.43  0.038264  0.126774   3.3132

#[10,] -0.19202 -0.106331 -0.036708    0.53    0.47  0.062871  0.288595   4.5903

#[11,]  0.08539  0.134945  0.183998    0.13    0.87  0.038129  0.080959   2.1233

#[12,]  0.41047  0.595387  0.788288    0.59    0.41  0.156244 -0.462017  -2.9570

#