About US Model User Datasets

July 30, 2020
The following discussion pertains to the version of the model dated January 30, 2020. New forecasts were not made on April 29, 2020, and July 30, 2020.

Forecast Period versus Prediction Period
We will use the phrase "forecast period" to refer to the actual forecast period in the base dataset, currently 2020:1-2025:4. You may, however, deal with any period within the overall 1952:1-2025:4 period, and we will use the phrase "prediction period" to refer to the period you have chosen. The only restriction is that if you are going to solve the model, the prediction period cannot begin earlier than 1954:1.

The US Model Datasets
Everything about the model is stored in a single dataset:

  • values on all the endogenous and exogenous variables from 1952:1 through 2025:4,
  • specification information, and
  • coefficient estimates.
The dataset for the January 30, 2020, update of the model is called ZAEBASE with a password USBASE. You will name and create your own dataset, using ZAEBASE as a starting point. Say you call your dataset NEW and give it the password of NEW. When you first start, NEW and ZAEBASE are exactly the same, and then NEW gets modified as you make changes (change exogenous variables, coefficients, etc.). Once you are done making changes, you tell the program to solve the model. The program solves the model, and after this solution, the values of the endogenous variables in NEW are the predicted values. You can examine (i.e., write to the screen, print to a printer, or download to a file) the values in ZAEBASE and in any datasets you create.

In many cases one is interested in how the values of the endogenous variables in NEW compare to the original values in ZAEBASE. Say that you changed federal government purchases of goods (COG) for the forecast period and are interested in how this change affected real GDP (GDPR). You can simply tell the program that you want to compare GDPR in NEW versus ZAEBASE, and it will show you the two sets of values and the differences. (Once you do this a few times you will get the hang of it.)
WARNING: If you do this comparison for any period beginning earlier than the beginning of the forecast period, you must use the option to use the historical errors. See Section 2.6 in Chapter 2 of The US Model Workbook, January 30, 2020 for more discussion.

The program is flexible as to what you take as your base dataset. Although the first time you start the base dataset is ZAEBASE, after you have created new ones, you can use any of these as your base. For example, if you created NEW and now want to makes further changes and create NEW1, you simply tell the program that you want NEW as your base dataset. Once you have created NEW1, you can either compare the values in NEW1 with those in NEW or the values in NEW1 with those in ZAEBASE. You do this by simply telling the program which two datasets to use for the comparison.

If you make changes to your dataset and do not ask the program to solve it (which you are allowed to do), the values of the endogenous variables in the dataset are not consistent with your changes because they are not the solution values. Make sure you remember whether your dataset has been solved. As a general rule, you might always solve your datasets immediately after you have made your changes.

Units of the Variables
The flow variables in the US model are at quarterly rates, and unless otherwise noted these are the units on the site. Much of the data presented by the government are at annual rates, and if you want annual rates, just multiply the flow variables by four.

Changing the Prediction Period
The default prediction period for the January 30, 2020, version of the model is 2020:1-2025:4. If you want to change this period, you can use the option "Set prediction period." For this option, however, you can only enter years, where the beginning of the prediction period is the first quarter of the first year and the end is the fourth quarter of the last year. If you want a different starting quarter, you can do this by going to the option "Take equations to begin after the beginning of the prediction period" and entering the quarter you want for all of the equations. For example, if you want the beginning to be the second quarter of 2008, you would enter 20082 for all of the equations.

The option "Change exogenous variables" does not have the year restriction. You can enter any quarter, like 20082, for the changes.

Solution Errors
If you make wild changes to the exogenous variables or coefficients, the model may not solve. When the model does not solve, you will get a solution error message, and the existing values of the endogenous variables in your dataset will not be changed. (Your dataset will still be inconsistent in the sense discussed above.) You need to be less wild and try again. As a general rule, you should not try to push the economy into extreme areas. Macroeconometric models are not likely to be reliable when variable values are pushed far beyond their historical ranges.

Examining the Output
If you change the display period from the default in the output part of the site, you are also restricted to entering only years. This is not, however, much of a restriction, since all you get are a few more quarters displayed than you might optimally want. Remember the base dataset for comparison is ZAEBASE with a password of USBASE.

Dataset Names and Storage
The dataset names cannot be longer than EIGHT characters. A common mistake is to use more than eight characters. The datasets are stored on the site's hard drive for about three months. If you want to continue to use a dataset older than three months, simply copy it to a new named dataset, and the latter will be treated as a newly created dataset.