Fair Model

Betty J. Blecha, San Francisco State University
Author Profile


The Fair model web site includes a freely available United States macroeconomic econometric model and a multicounty econometric model. The models run on the Windows OS. Instructors can use the models to teach forecasting, run policy experiments, and evaluate historical episodes of macroeconomic behavior. The web site includes extensive documentation for both models. The simulation is for upper-division economics courses in macroeconomics or econometrics. The principle developer is Ray Fair at Yale University.

Learning Goals

The Fair model is the granddaddy of PC forecasting models. The first version, freely available for download, was posted in 1982. It is also a simulation model with a long professional history that continues to be updated and used for current forecasts. The current forecast memo is available on the Fair model web site .

Instructors who have used the Fair model over the years have had a variety of learning goals:

  • Show students a small macroeconomic forecasting model with current forecasts: The purpose here is often limited to a demonstration or a discussion of the current forecast memo. The model remains a "black box" for instructional purposes.
  • Let students do their own forecast: This requires a detailed discussion of how the model is structured and some hands-on help from the instructor on how to solve the model.
  • Simulate past historical episodes: This use of the model is particularly relevant for courses with a strong macroeconomic policy component. Students can simulate a variety of policy variables to see how the endogenous variables change. These changes can be compared with the actual time paths of the endogenous variables.
  • Contrast an empirical macroeconomic model with a calibrated macroeconomic model: One suspects that the recent recession will give new life to this debate.

Context for Use

The Fair model is most appropriate for an intermediate macroeconomics course or an applied econometrics course. The more focused the instructional goals become on actual forecasting, the more important it becomes to require mathematical and statistical prerequisites for students.

Description and Teaching Materials

An instructor interested in using the Fair model should look at Ray Fair's page first. The page contains several interesting items with instruction content. The direct link to the model page itself is the Fair model support page. After navigating to the support page, a new user of the Fair model should first look at the "Getting Started" section. In the "Getting Started" section, the "U.S. Model Workbook" is the first section to read for new users.

The following information from the download section describes the solution program for the U.S. model that is implemented by a DOS command-line program.

  • "The Fair-Parke (FP) program is a DOS-based, command-line program. It allows one to estimate and analyze dynamic, nonlinear, simultaneous equations models. The models can be rational expectations models, and they can have autoregressive errors of any order. The estimation techniques include OLS, 2SLS, 3SLS, FIML, LAD, 2SLAD, and some versions of Hansen's method of moments estimator. The Parke algorithm is used for 3SLS and FIML estimation. Stochastic simulation and bootstrapping are two of the key options available to analyze models. There are also a number of single equation testing options. For stochastic simulation the draws can be either from estimated distributions or from estimated residuals."
  • "The options for analyzing models include 1) running forecasts, within sample and outside sample, 2) calculating root mean squared errors and mean absolute errors, 3) calculating multipliers, 4) solving optimal control problems, 5) estimating standard errors of forecasts by means of stochastic simulation, 6) estimating standard errors of multipliers by means of stochastic simulation, and 7) estimating the degree of misspecification of a model by means of successive reestimation and stochastic simulation. Also, general nonlinear functions of coefficients can be maximized using the program, which means that maximum likelihood estimates of the coefficients of any model can be obtained after one has written out the likelihood function."

TIME REQUIREMENT: Dependent on the instructional use of the model.

Teaching Notes and Tips

Because the Fair model has a professional history, assignments can be linked to this history:
  • The forecast memo archive can be the source for a lively class discussion about the strengths and weaknesses of macroeconomic forecasts.
  • An EconLit search yields the recent professional discussions of the Fair model. The abstracts give students an excellent view of the types of professional discussions generated by macroeconomic forecasting models.


All traditional assessment tools can be used. For more information about assessment, see the SERC assessment module.

References and Resources

Fair, R.C. (2004). Estimating How the Macroeconomy Works. Harvard University Press.

Fair, R.C. (2002). Predicting Presidential Elections and Other Things. Stanford Economics and Finance.