## AR term in multivariant GARCH model

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

JerryWC
Posts: 2
Joined: Sat May 19, 2018 11:21 pm

### AR term in multivariant GARCH model

Hello,
How to incorporate AR(1) in multivariant GARCH estimations?
I input "AR(1)" in Common coefficients of Regressor and AR() terms under Make System window, the code becomes
-------------------------------------
@STACKINST
@INST
DLN_CNH = C(1) + [AR(1)=C(2)]
DLN_CNY = C(3) + [AR(1)=C(2)]
--------------------------------------
which means I will have same coeff("C(2)") for AR(1) term of the two equation.

I try to revise the code below, but shows "AR is not defined in "DLN_CNH = C(1) + C(3)*AR(1)"
---------------------------------------
@STACKINST
@INST
DLN_CNH = C(1) + C(3)*AR(1)
DLN_CNY = C(2) + C(4)*AR(1)
--------------------------------------

Can anyone help on this ? many thanks ~

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 11981
Joined: Tue Sep 16, 2008 5:38 pm

### Re: AR term in multivariant GARCH model

Bit confused. Do you want the AR terms to have the same coefficient? If not, why did you enter it as a "Common coefficient"?

But, if you don't want them to have the same coefficient, change the coefficient in the specification from C(2) to something else.

JerryWC
Posts: 2
Joined: Sat May 19, 2018 11:21 pm

### Re: AR term in multivariant GARCH model

Hello ~ I revised the code below and re-run, and it works! though freq shut-down maybe due to Microsoft issues. My head must be swimming... thanks for the reply again.

_____________________________________
@STACKINST
@INST
DLN_CNH = C(1) + [AR(1)=C(2)]
DLN_CNY = C(3) + [AR(1)=C(4)]
_____________________________________