这个问题我曾以数据hp_ibm.txt回答过
hp_ibm.txt在50楼
https://bbs.pinggu.org/thread-1127506-5-1.html
s-plus有算出se,t,p-value
matlab需要自己运算
%%%%%%%
s-plus
Modelling Financial Time Series with S-PLUS
page 516/1016
module("finmetrics")
hp.ibm = seriesMerge(hp.s, ibm.s)
hp.ibm=100*hp.ibm
hp.ibm.bekk = mgarch(hp.ibm~-1, ~bekk(1,1))
hp.ibm.bekk
Call:
mgarch(formula.mean = hp.ibm ~ -1, formula.var = ~ bekk(1, 1))
Mean Equation: structure(.Data = hp.ibm ~ -1, class = "formula")
Conditional Variance Equation: structure(.Data = ~ bekk(1, 1),class = "formula")
Coefficients:
A(1, 1) 0.74486
A(2, 1) -0.34202
A(2, 2) 0.47969
ARCH(1; 1, 1) 0.20091
ARCH(1; 2, 1) -0.02610
ARCH(1; 1, 2) -0.05714
ARCH(1; 2, 2) 0.41349
GARCH(1; 1, 1) 0.82645
GARCH(1; 2, 1) 0.12095
GARCH(1; 1, 2) 0.25594
GARCH(1; 2, 2) 0.70165
%%%%%%%%%%%%%%%%matlab
load('hp_ibm.txt')
data=100*hp_ibm;
[parameters, loglikelihood, Ht, likelihoods, stdresid, stderrors, A, B, scores] = full_bekk_mvgarch(data,1,1);
parameters
parameters =
0.6971
-0.3355
0.5062
0.1955
-0.0242
-0.0369
0.4192
0.8438
0.1163
0.2327
0.6977