july0710 发表于 2013-4-5 09:53 
能不能帮忙看下这个问题
data(dji30ret)
spec = gogarchspec(mean.model = list(model = c("constant", "AR", "VAR")[2],
lag =1), variance.model = list(model = "gjrGARCH", garchOrder = c(1, 1),
submodel = NULL, variance.targeting = FALSE), distribution.model = c("mvnorm",
"manig", "magh")[2], ica = c("fastica", "radical")[1])
fit1 = gogarchfit(spec,
data = dji30ret[,1:4, drop = FALSE], out.sample = 0, gfun = "tanh", rseed = 7)
fit1
*------------------------------*
* GO-GARCH Fit *
*------------------------------*
Mean Model : AR
(Lag) : 1
GARCH Model : gjrGARCH
Distribution : manig
ICA Method : fastica
No. Factors : 4
No. Assets : 5520
Log-Likelihood : 59164.22
------------------------------------
U (rotation matrix) :
[,1] [,2] [,3] [,4]
[1,] 0.433 0.6016 -0.321 -0.590
[2,] -0.778 0.1245 0.231 -0.571
[3,] -0.426 0.0929 -0.864 0.252
[4,] -0.159 0.7836 0.312 0.513
A (mixing matrix) :
[,1] [,2] [,3] [,4]
[1,] -0.02172 -0.00649 0.00241 0.00337
[2,] -0.00211 -0.02156 0.00323 0.00720
[3,] -0.00371 -0.00398 0.01855 0.00282
[4,] -0.00317 -0.00627 0.00255 0.02295