Working Paper

Can Forecast Errors Predict Financial Crises? Exploring the Properties of a New Multivariate Credit Gap


Abstract: Yes, they can. I propose a new method to detect credit booms and busts from multivariate systems -- monetary Bayesian vector autoregressions. When observed credit is systematically higher than credit forecasts justified by real economic activity variables, a positive credit gap emerges. The methodology is tested for 31 advanced and emerging market economies. The resulting credit gaps fit historical evidence well and detect turning points earlier, outperforming the credit-to-GDP gaps in signaling financial crises, especially at longer horizons. The results survive in real time and can shed light on the drivers of credit booms.

Keywords: Credit gap; Early warning; Credit boom; Conditional forecast; Financial crisis; Bayesian VAR;

JEL Classification: E58; C11; C53; C13; E51;

https://doi.org/10.17016/FEDS.2020.045

Access Documents

Authors

Bibliographic Information

Provider: Board of Governors of the Federal Reserve System (U.S.)

Part of Series: Finance and Economics Discussion Series

Publication Date: 2020-06-12

Number: 2020-045

Pages: 65 p.