|
nobs <- 1000; cut <- 1000; nu <- 10
a <- c(0.003, 0.005, 0.001)
A <- diag(c(0.2,0.3,0.15))
B <- diag(c(0.79, 0.6, 0.8))
R <- matrix(c(1.0, 0.4, 0.3, 0.4, 1.0, 0.12, 0.3, 0.12, 1.0),3,3)
ccc.data <- eccc.sim(nobs,a, A, B, R, model="diagonal")
ccc.data.t <- eccc.sim(nobs,a, A, B, R, d.f=nu, model="diagonal")
eccc.results <- eccc.estimation(a=a, A=A, B=B, R=R,dvar=ccc.data$eps, model="diagonal")
# Parameter estimates and three different methods of standard errors
eccc.results$out
#the estimated conditional variances
eccc.results$h
#####Parameter estimates and three different methods of standard errors
a1 a2 a3 A11 A22
para.estimates 0.003030526 0.003977575 0.001554368 0.237203942 0.2680961351
Inv. Hessian 0.001085805 0.017680594 0.016964872 0.052755978 0.0009377996
Outer Prod. 0.001078943 0.033891052 0.028677725 0.001029508 0.0396503868
Robust 0.073244016 0.124493185 0.588765330 6.884022176 0.1716013970
A33 B11 B22 B33 R21
para.estimates 0.134429680 0.758944199 0.657223915 0.75742740 0.36428882
Inv. Hessian 0.001701617 0.027548529 0.003314058 0.01459839 0.02733618
Outer Prod. 0.044371109 0.000588581 0.035112225 0.06793994 0.02911398
Robust 0.004298446 6.034257035 0.006373360 0.04019659 0.57303606
R31 R32
para.estimates 0.34243345 0.20610363
Inv. Hessian 0.02787193 0.03023527
Outer Prod. 0.02797334 0.02969068
Robust 0.16786669 0.35844037
#####the estimated conditional variances
[,1] [,2] [,3]
[1,] 0.15418287 0.04556739 0.014239821
[2,] 0.14147896 0.03442299 0.016008914
[3,] 0.11144658 0.03243635 0.013793144
.....
.....
[998,] 0.05524098 0.06826931 0.009779935
[999,] 0.04706783 0.05544999 0.008984986
[1000,] 0.04595090 0.12242765 0.009424343
|