ARMA equation

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

Posts: 1
Joined: Tue Aug 28, 2018 3:19 am

ARMA equation

Postby guido » Tue Aug 28, 2018 6:36 am

I struggle to understand the difference between this two models, when generating an equation in EViews:

gdp gdp(-1) gdp(-2)
gdp ar(1) ar(2)

Are not those the same? Unfortunately EViews returns different values, especially when I add a constant and a trend.

Non-normality and collinearity are NOT problems!
Posts: 3418
Joined: Wed Sep 17, 2008 2:25 pm

Re: ARMA equation

Postby startz » Tue Aug 28, 2018 7:08 am

AR terms refer to lags of the error term. In an equation with no error term, that's the same as lags of the dependent variable. Otherwise not.

The other difference is that by default EViews uses slightly different estimation techniques for AR than for lags. Generally, it makes very little difference.

Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 9 guests