Forecasting U.S. Economic Activity with a Small Information Set 
This paper shows how a parsimonious set of fundamentals capturing important macroeconomic dynamics—the unemployment rate, a measure of consumer sentiment, the federal funds rate, and a corporate credit risk spread—can generate forecasts for the unemployment rate and GDP growth that, over relatively long time periods, are about as accurate as private-sector and Federal Reserve Board forecasts. Relative to other forecasting benchmarks explored in the literature, such as univariate autoregressive models or atheoretical methods involving a large amount of data, this approach has the advantage of providing a forecast narrative that, albeit simple, is based on macroeconomic fundamentals that monetary policymakers view as crucial components of the forecasting process.
Key Findings
- The authors’ parsimonious approach to forecasting performs well for the 1984–2019 period and for the post-pandemic period of 2021 through 2024.
- However, such an outcome requires imposing an Okun’s law relationship on the joint behavior of the unemployment rate and GDP—a result that could also prove relevant for improving forecasting performance in other settings.
Implications
The paper’s results show how a parsimonious set of information about the labor market, consumer sentiment, the interest rate environment, and credit market sentiment is important for forecasting GDP growth and the unemployment rate. It is therefore possible that using alternative measures that better summarize relevant conditions along these four dimensions would yield forecasts that are even more accurate.
Abstract
We provide a parsimonious setup for forecasting U.S. GDP growth and the unemployment rate based on a few fundamental drivers. This setup yields forecasts that are reasonably accurate compared with private-sector and Federal Reserve forecasts over the 1984–2019 and post–COVID-19 pandemic periods. This result is achieved by jointly estimating the processes for GDP growth and the unemployment rate, with the constraint that GDP and unemployment follow Okun’s law in first differences. This setup can be easily extended to replace the variables in the information set with factors that might better capture the underlying fundamentals.