請問rats varma garch 的 LM test 要怎麼做??
我的程式碼如下了
open data 1.xlsx
data(format=xlsx,org=columns) 1 1961 US JAP ELEC FIN PLAS MACH GLASS Chemicals D08
system(model=var1)
variables US ELEC
lags 1
det constant
end(system)
garch(p=1,q=1,model=var1,mv=CC,variances=varma,pmethod=simplex,piters=10,hmatrices=hh,rvectors=rr)
MV-GARCH, CC with VARMA Variances - Estimation by BFGS
Convergence in 42 Iterations. Final criterion was 0.0000076 <= 0.0000100
Usable Observations 1960
Log Likelihood 17613.0485
Variable Coeff Std Error T-Stat Signif
************************************************************************************
1. US{1} -4.0779e-003 0.0227 -0.17941 0.85761335
2. ELEC{1} -0.0103 4.1091e-003 -2.51232 0.01199412
3. Constant -3.1845e-005 2.6592e-005 -1.19753 0.23109898
4. US{1} -0.2283 0.0842 -2.71122 0.00670353
5. ELEC{1} 0.0466 0.0239 1.94458 0.05182546
6. Constant 1.6447e-004 1.1387e-004 1.44429 0.14865880
7. C(1) 1.0585e-008 1.0726e-008 0.98683 0.32372475
8. C(2) 6.1484e-007 2.0908e-007 2.94069 0.00327483
9. A(1,1) 0.0984 0.0135 7.30931 0.00000000
10. A(1,2) 8.6748e-003 2.3551e-003 3.68332 0.00023021
11. A(2,1) 0.0966 0.0551 1.75523 0.07921937
12. A(2,2) 0.0810 0.0120 6.77813 0.00000000
13. B(1,1) 0.8709 0.0165 52.75831 0.00000000
14. B(1,2) -0.0342 8.9595e-003 -3.81271 0.00013745
15. B(2,1) -0.0984 0.1650 -0.59626 0.55100109
16. B(2,2) 0.9054 0.0162 56.04711 0.00000000
17. R(2,1) -0.2908 0.0203 -14.34115 0.00000000
set stdUS = rr(t)(1)/sqrt(hh(t)(1,1))
set stdELEC = rr(t)(2)/sqrt(hh(t)(2,2))
@mvqstat(lags=12)
# stdUS
@mvqstat(lags=12)
# stdELEC
@mvqstat(lags=12)
# stdUS stdELEC
set stdUSsq = stdUS**2
set stdELECsq = stdELEC**2
@mvqstat(lags=12)
# stdUSsq
@mvqstat(lags=12)
# stdELECsq
@mvqstat(lags=12)
# stdUSsq stdELECsq
------------------------------------------------------------------------------
再請問
為何我接下來輸入這個
set rho12=hh(t)(1,2)/sqrt(hh(t)(1,1)*hh(t)(2,2))出現下面
## SX22. Expected Type SERIES[REAL], Got REAL Instead>>>>)*sqrt(hh(t)(2,2))<<<<請問我是哪裡還需要更改??謝謝
附上檔案~謝謝!!!!