Skip to main content

A dynamic factor model framework for forecast combination


A panel of ex-ante forecasts of a single time series is modeled as a dynamic factor model, where the conditional expectation is the single unobserved factor. When applied to out-of-sample forecasting, this leads to combination forecasts that are based on methods other than OLS. These methods perform well in a Monte Carlo experiment. These methods are evaluated empirically in a panel of simulated real-time computer-generated univariate forecasts of U.S. macroeconomic time series.

This is a preview of subscription content, access via your institution.

Author information

Authors and Affiliations


Rights and permissions

Reprints and Permissions

About this article

Cite this article

Chan, Y., Stock, J. & Watson, M. A dynamic factor model framework for forecast combination. Span Econ Rev 1, 91–121 (1999).

Download citation

  • Issue Date:

  • DOI:

  • JEL classification: C32, C22
  • Key words: Combination forecasts, principal component regression, James-Stein estimation