843978571 发表于 2013-1-18 01:01 
我记得使用这个模型的论文用的是BHHH算法,有好几个都是
ug-208已经说得很清楚了
Estimation Methods are BFGS, BHHH, SIMPLEX and GENETIC,
default is BFGS.
If you want the BHHH covariance matrix, it’s better to use BFGS as a preliminary
method, then switch to BHHH for a final iteration once it’s converged. The derivativefree
methods (SIMPLEX and GENETIC) are very useful in multivariate garch models,
but aren’t quite as important with the univariate ones. However, if you’re having
convergence problems with BFGS or BHHH, you can use the PMETHOD option with SIMPLEX
or GENETIC and combined with PITERS to refine the initial guesses
换句话说楼主贴出来的程序和结果是不相符的
system(mode1=var1)
variables err szr sbr
lags 1
det constant
end(system)
garch(p=1,q=1,mode1=var1,mv=bekk,pmethod=bhhh,piters=10)
MV-GARCH, BEKK - Estimation by
BHHH ???
******
应该是
garch(p=1,q=1,model=var1,mv=bekk,pmethod=bhhh,piters=10)
MV-GARCH, BEKK -
Estimation by BFGS
******
底下范例
使用BFGS,BHHH的结果是相同的
open data g10xrate.xls
data(format=xls,org=columns) 1 6237 usxjpn usxfra usxsui
set xjpn = 100.0*log(usxjpn/usxjpn{1})
set xfra = 100.0*log(usxfra/usxfra{1})
set xsui = 100.0*log(usxsui/usxsui{1})
system(model=var1)
variables xjpn xfra xsui
lags 1
det constant
end(system)
garch(p=1,q=1,model=var1,mv=bekk,pmethod=simplex,piters=10)
*MV-GARCH, BEKK -
Estimation by BFGS
*Convergence in 104 Iterations. Final criterion was 0.0000095 <= 0.0000100
*Usable Observations 6235
*Log Likelihood
-11809.4143
garch(p=1,q=1,model=var1,mv=bekk,method=bhhh,pmethod=simplex,piters=10)
*MV-GARCH, BEKK -
Estimation by BHHH
*Convergence in 110 Iterations. Final criterion was 0.0000029 <= 0.0000100
*Usable Observations 6235
*Log Likelihood
-11809.4145
Variable Coeff Std Error T-Stat Signif
************************************************************************************
1. XJPN{1} 0.054056756 0.011157196 4.84501 0.00000127
2. XFRA{1} 0.023692552 0.012767254 1.85573 0.06349232
3. XSUI{1} -0.034347414 0.009122370 -3.76519 0.00016643
4. Constant 0.006201308 0.005803445 1.06856 0.28526957
5. XJPN{1} 0.028502333 0.011319085 2.51808 0.01179974
6. XFRA{1} 0.023733022 0.009892819 2.39901 0.01643924
7. XSUI{1} -0.009374605 0.006832107 -1.37214 0.17001996
8. Constant -0.001862654 0.004674356 -0.39848 0.69027378
9. XJPN{1} 0.040988355 0.013943092 2.93969 0.00328542
10. XFRA{1} 0.025029943 0.009888338 2.53126 0.01136540
11. XSUI{1} -0.017967277 0.009367145 -1.91812 0.05509620
12. Constant -0.001915049 0.005577392 -0.34336 0.73132830
13. C(1,1) 0.080420169 0.004844832 16.59917 0.00000000
14. C(2,1) 0.026792535 0.007153359 3.74545 0.00018007
15. C(2,2) 0.055092810 0.005136386 10.72599 0.00000000
16. C(3,1) 0.034174635 0.007952256 4.29748 0.00001728
17. C(3,2) -0.004064308 0.010069368 -0.40363 0.68648419
18. C(3,3) -0.058668020 0.006546375 -8.96191 0.00000000
19. A(1,1) 0.356742939 0.011175929 31.92065 0.00000000
20. A(1,2) 0.099023385 0.009312906 10.63292 0.00000000
21. A(1,3) 0.107358980 0.012538272 8.56250 0.00000000
22. A(2,1) 0.033523234 0.015000487 2.23481 0.02542984
23. A(2,2) 0.398493512 0.017986175 22.15555 0.00000000
24. A(2,3) -0.070349572 0.019349112 -3.63580 0.00027712
25. A(3,1) -0.047186040 0.010155983 -4.64613 0.00000338
26. A(3,2) -0.122496143 0.012604129 -9.71873 0.00000000
27. A(3,3) 0.292924401 0.014013391 20.90318 0.00000000
28. B(1,1) 0.936391469 0.003747744 249.85472 0.00000000
29. B(1,2) -0.025328191 0.003246968 -7.80057 0.00000000
30. B(1,3) -0.027021572 0.004178229 -6.46723 0.00000000
31. B(2,1) -0.010662124 0.005817199 -1.83286 0.06682308
32. B(2,2) 0.911892529 0.007065422 129.06413 0.00000000
33. B(2,3) 0.030714339 0.007142836 4.30002 0.00001708
34. B(3,1) 0.016113773 0.004334369 3.71767 0.00020107
35. B(3,2) 0.047482017 0.005627813 8.43703 0.00000000
36. B(3,3) 0.946088918 0.005435624 174.05342 0.00000000