P-values for Vector Autoregressions

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

Damien Kunjal
Posts: 3
Joined: Tue Sep 17, 2019 1:25 am

P-values for Vector Autoregressions

Postby Damien Kunjal » Tue Oct 22, 2019 6:00 am

Dear all,

Is it possible to obtain P-values for VAR (Vector Autoregression) coefficients? The regression output displays the standard error and t-statistics, however, I am trying to obtain the P-values. Is this possible, and if it is, what is the process?

Thank you all.

EViews Matt
EViews Developer
Posts: 560
Joined: Thu Apr 25, 2013 7:48 pm

Re: P-values for Vector Autoregressions

Postby EViews Matt » Tue Oct 22, 2019 10:00 am

Hello,

I don't believe the p-values are available from a VAR object. I believe you'd need to write a program to go through the results table, extract each t-statistic, and calculate the corresponding p-value.

Damien Kunjal
Posts: 3
Joined: Tue Sep 17, 2019 1:25 am

Re: P-values for Vector Autoregressions

Postby Damien Kunjal » Thu Oct 24, 2019 2:11 am

Thank you for your assistance, Matt. 8)

JuanNicolasDamico
Posts: 6
Joined: Mon Dec 14, 2020 9:26 am

Re: P-values for Vector Autoregressions

Postby JuanNicolasDamico » Fri Jan 01, 2021 6:32 pm

You can.

After you estimate the VAR model, go to the top Menu and select>PROC>MAKE SYSTEM>ORDER BY VARIABLE. A new window will show up, and you should select "Estimate" in the menu bar ( where it says VIEW-PROC-OBJECT--- select estimate), and then click "Ok". (The estimation method is OLS, which is good).

For further details on VAR models you can check the following step by step paper replica of a VAR model: https://youtu.be/SbE8ns0oOTs

Cheers


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 29 guests