Checking consistency with a steady state path

For technical support, tips and tricks, suggestions, or any other information regarding the EViews model object.

Moderators: EViews Gareth, EViews Moderator

jlbrillet
Posts: 39
Joined: Mon Feb 16, 2009 6:03 am

Checking consistency with a steady state path

Postby jlbrillet » Thu Jun 14, 2012 4:27 am

- How to check that your assumptions and equations conform to a steady state path in simulations over the future.

You just create assumptions for all endogenous and exogenous using consistent and constant growth rates, according to the dimension of the variable (like 0 for ratios, 2% for quantities, 3% for inflation, 0.5% for populations...).

Then you simulate the model over the future using independent computations (the "fit" option, with d=f) and compute the growth rate of the result. If the difference to the growth rate of the left hand assumption is not zero, there is at least one error in that particular equation.

Note : there can be more than one, and a zero residual can hide to compensating errors (like forgetting an element in both equation and variable value).

If all your equations are OK, and you use error correction framework, your model should converge to the steady state (except if the short run dynamics are explosive).

Return to “Models”

Who is online

Users browsing this forum: No registered users and 1 guest