The US Model in EViews

US Model for EViews: January 31, 2025, version of the US model

If you have EViews on your computer and want to work with the January 31, 2025, version of the US model in EViews, you can do this by downloading the zipped file
usev244.zip.
You should download this file by clicking it, and then unzip it. The .wf1 file is the EViews workfile. The workfile includes two models. fma_ev_rs_exog takes RS to be exogenous. The other model includes equation 30 and so takes RS to be endogenous. This is the model for the forecast on the site. The predictions using this model should be close to the "actuals" which are the predictions of the FAIR model on the website. Note that when preforming policy experiments, the alternative scenario (_1) should be compared to a baseline scenario (_0) rather than to the "actuals" to avoid conflating minor differences between the EVIEWS version and the FAIR version, with the changes due to the policy experiment.

This work is due to Matthew Cushing at the University of Nebraska-Lincoln. The readme.txt file below is discussion from Matt. Matt has also added this note:

readme.txt:

The included workfile is optimized to take advantage of a number of 
features of Eviews. 

1. The EVIEWS version provides a great deal of flexibility in solving and modifying 
the model. Simply clicking on fma_ev and solving over the default sample reproduces
the FAIRPARK predictions.  (The future actuals are the FAIRPARK prediction. The baseline 
predictions from the fma_ev model are very close to the FAIRPARK predictions.) You are then
free to use all the features of EVIEWS to modify the model, do stochastic predictions or
perform counterfactuals of historic periods.

2. This version exploits EVIEWS's ability to recognize simple functions in 
regression commands. The equations are easy to interpret and the workfile is not 
cluttered with generated variables. Coefficient restriction are made explicit in 
equations 16, 23 and 24, rather than imposed by redefining variables. 

3. Variables have labels and equations have more understandable names. Clicking 
on the Details tab brings up the description of each variable.

4. The variables COS and AR are renamed COSS and ARR because COS and AR are reserved
 names in EVIEWS.

7. Identities are labelled as such.  This is useful in making add factors and 
doing stochastic simulations. 

end of readme.txt

EViews Archive

EViews Archive