Download Article

RWP 18-13, December 2018; Updated June 2021

Expectations about future economic conditions play a central role in macroeconomic theory. These expectations are empirically measured from surveys or financial markets and then are frequently analyzed in Vector autoregression (VAR) models alongside realized data of the same variable. However, jointly analyzing realized data and external forecasts in a VAR leads to the simultaneous existence of two different expectations of the same variable: the VAR-based forecast and the survey or market forecast. This paper proposes a Bayesian prior over the VAR parameters which allows the econometrician to impose the desired degree of consistency between these two forecasts. Our approach leverages the existence of multiple forecasts to aid in structural VAR identification and enhance VAR forecasts. We illustrate the usefulness of our approach in two applications exploring the identification of forward guidance shocks and the role that inflation expectations played in shaping inflation tail-risks during the Great Recession and its aftermath.

Additional Files: PDFAppendix

JEL Classification: C11, C32, E52, E31

Article Citation

  • Doh, Taeyoung, and A. Lee Smith. “A New Approach to Integrating Expectations into VAR Models.” Federal Reserve Bank of Kansas City, Research Working Paper no. 18-13, December; updated October 2020. Available at External Link


Taeyoung Doh

Senior Economist

Taeyoung Doh is a Senior Economist in the Economic Research Department of the Federal Reserve Bank of Kansas City. He joined the department in July 2007. He received a bachelor&#…

A. Lee Smith

Vice President and Economist

Andrew Lee Smith is a Vice President and Economist in the Economic Research Department of the Federal Reserve Bank of Kansas City. Prior to joining the department in 2014, Mr. Sm…