Page 2 of 2
Re: trivariate DCC with VAR(1) MEAN EQUATIONS
Posted: Thu Jun 18, 2009 8:21 pm
by xyzh
Here's an example paper:
http://ideas.repec.org/a/eee/quaeco/v47 ... l#download
Hope u will understand what i said.
Thanks.
Zhang
Re: trivariate DCC with VAR(1) MEAN EQUATIONS
Posted: Sun Jun 21, 2009 6:52 am
by xyzh
moderator wrote:Including asymmetry terms is covered in the manuals. See "GARCH" in the Reference Manual and Chapter 12 in the User's Guide.
the manual demonsrates the GJR ,right?
My question is about estimating a ADCC model, am I right?
Tks.
Zhang
Re: trivariate DCC with VAR(1) MEAN EQUATIONS
Posted: Tue Jul 14, 2009 1:26 pm
by xyzh
I have a new problem now with the MVGARCH-DCC. After adding "variance=varma" option i got the results like this:
- Variable Coeff Std Error T-Stat Signif
*******************************************************************************
1. Mean(1) 0.000145192 0.000298354 0.48664 0.62651077
2. Mean(2) 0.000452759 0.000251361 1.80123 0.07166673
3. Mean(3) 0.000307494 0.000043419 7.08208 0.00000000
4. C(1) -0.000000217 0.000000529 -0.41026 0.68161615
5. C(2) 0.000000710 0.000000564 1.25993 0.20769582
6. C(3) 0.000000155 0.000000045 3.42794 0.00060818
7. A(1,1) 0.057933592 0.016794974 3.44946 0.00056171
8. A(1,2) -0.065924827 0.025252117 -2.61067 0.00903663
9. A(1,3) 0.048611966 0.132020640 0.36821 0.71271301
10. A(2,1) -0.031016545 0.016435385 -1.88718 0.05913600
11. A(2,2) 0.102465005 0.025064940 4.08798 0.00004351
12. A(2,3) -0.096694866 0.135042222 -0.71603 0.47397015
13. A(3,1) 0.005105719 0.005538758 0.92182 0.35662423
14. A(3,2) 0.009217814 0.006968065 1.32287 0.18588005
15. A(3,3) 0.098969648 0.028962153 3.41721 0.00063267
16. B(1,1) 0.904499342 0.023065961 39.21360 0.00000000
17. B(1,2) 0.196648202 0.052423936 3.75111 0.00017605
18. B(1,3) -2.498101504 0.993974355 -2.51325 0.01196261
19. B(2,1) 0.063046957 0.030820503 2.04562 0.04079403
20. B(2,2) 0.872904440 0.031369087 27.82690 0.00000000
21. B(2,3) -0.260539758 0.444913701 -0.58560 0.55814692
22. B(3,1) -0.091754291 0.037002318 -2.47969 0.01314965
23. B(3,2) 0.020923602 0.030008992 0.69724 0.48564984
24. B(3,3) 0.851193338 0.033443870 25.45140 0.00000000
25. DCC(1) 0.009226038 0.003358069 2.74742 0.00600656
26. DCC(2) 0.988152157 0.006115655 161.57750 0.00000000
27. Shape 8.273972673 1.325200506 6.24356 0.00000000
Im confused what the non-diagonal elements mean?
Re: trivariate DCC with VAR(1) MEAN EQUATIONS
Posted: Tue Jul 14, 2009 9:28 pm
by TomDoan
That's explained in the manual. VARIANCES=VARMA is an extension of the CC/DCC type model allowing each variance to depend upon the other variances and the other lagged squared residuals. Those terms give those off-diagonal coefficients.
Re: trivariate DCC with VAR(1) MEAN EQUATIONS
Posted: Thu Aug 06, 2009 3:32 am
by gembala119
Dear Sir
After we do trivariate or bivariate garch model, how we make graphs of variance and covariance of bivariate or trivariate
thank you very much
kim
Re: trivariate DCC with VAR(1) MEAN EQUATIONS
Posted: Thu Aug 06, 2009 3:38 am
by xyzh
gembala119 wrote:Dear Sir
After we do trivariate or bivariate garch model, how we make graphs of variance and covariance of bivariate or trivariate
kim
you can graph the variance and covariance with RATs by using the command "graph" plus some options or you can print the results and graph it with Excel.
Re: trivariate DCC with VAR(1) MEAN EQUATIONS
Posted: Thu Aug 06, 2009 9:37 am
by TomDoan
gembala119 wrote:Dear Sir
After we do trivariate or bivariate garch model, how we make graphs of variance and covariance of bivariate or trivariate
thank you very much
kim
This is from GARCHMV.PRG which graphs the correlations from a multivariate GARCH, with grid lines at the CC estimates.
Code: Select all
*
* GARCHMV.PRG
* Manual Example 12.2
*
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})
*
garch(p=1,q=1,iters=200,hmatrices=hh) / xjpn xfra xsui
garch(p=1,q=1,mv=bek,method=bfgs,iters=200,pmethod=simplex,piters=10) / xjpn xfra xsui
garch(p=1,q=1,mv=diag,hmatrices=hd,rvectors=rd) / xjpn xfra xsui
garch(p=1,q=1,mv=cc) / xjpn xfra xsui
garch(p=1,q=1,mv=dcc,method=bfgs) / xjpn xfra xsui
*
* Compute the covariance matrix of the standardized residuals from
* the diagonal GARCH
*
set z1 = rd(t)(1)/sqrt(hd(t)(1,1))
set z2 = rd(t)(2)/sqrt(hd(t)(2,2))
set z3 = rd(t)(3)/sqrt(hd(t)(3,3))
vcv(matrix=cc)
# z1 z2 z3
*
* Compute the correlations from the multivariate GARCH
*
set rho12 = hh(t)(1,2)/sqrt(hh(t)(1,1)*hh(t)(2,2))
set rho13 = hh(t)(1,3)/sqrt(hh(t)(1,1)*hh(t)(3,3))
set rho23 = hh(t)(2,3)/sqrt(hh(t)(2,2)*hh(t)(3,3))
graph(header="Correlation of JPN with FRA",vgrid=||cc(1,2)||)
# rho12
graph(header="Correlation of JPN with SUI",vgrid=||cc(1,3)||)
# rho13
graph(header="Correlation of FRA with SUI",vgrid=||cc(2,3)||)
# rho23
You also might want to look at tsayp452.prg from the Tsay textbook examples.