hi, i am regressing a var on a panel data, using 2-3 dependent variable with 4 lags.
I would like to test if the coefficents of the lagged dependent variables are jointly equal to zero (i.e. c(5)+c(4)+c(3)+c(2)=0).
do you know how can i write it?
thanks
wald test in a Var
Moderators: EViews Gareth, EViews Moderator
-
EViews Gareth
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13603
- Joined: Tue Sep 16, 2008 5:38 pm
Re: wald test in a Var
You can turn your VAR into a system object (proc->make system), and then from the system you can perform a wald test (view->coefficient diagnostics).
You should note that you could be careful running a VAR on a panel data set. EViews does not perform what are typically called "panel VAR" estimators. It just performs a regular VAR.
You should note that you could be careful running a VAR on a panel data set. EViews does not perform what are typically called "panel VAR" estimators. It just performs a regular VAR.
Re: wald test in a Var
i can not find view->coefficient diagnostics ion the system.
I run an alternative solution: I am scomposing the VAR as two different simple equation and i apply the wald on it simply changing the dependent variable. what do u think?
why u say it does not perform panel Var estimation? I manage to categorize in the workfile my data as panel and then i run a var on it. is it this enough?
I run an alternative solution: I am scomposing the VAR as two different simple equation and i apply the wald on it simply changing the dependent variable. what do u think?
why u say it does not perform panel Var estimation? I manage to categorize in the workfile my data as panel and then i run a var on it. is it this enough?
-
EViews Gareth
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13603
- Joined: Tue Sep 16, 2008 5:38 pm
Re: wald test in a Var
Composing it as two separate equations will work too.
As I said, you can run a VAR on panel data in EViews, but it does regular VAR estimation, not "panel VAR" estimation.
As I said, you can run a VAR on panel data in EViews, but it does regular VAR estimation, not "panel VAR" estimation.
Who is online
Users browsing this forum: No registered users and 1 guest
