Variance Decomposition Networks: Potential Pitfalls and a Simple Solution

May 4, 2017

Preview Citation

Format: Chicago

Jorge A Chan-Lau. Variance Decomposition Networks: Potential Pitfalls and a Simple Solution, (USA: International Monetary Fund, 2017) accessed September 19, 2024

Disclaimer: IMF Working Papers describe research in progress by the author(s) and are published to elicit comments and to encourage debate. The views expressed in IMF Working Papers are those of the author(s) and do not necessarily represent the views of the IMF, its Executive Board, or IMF management.

Summary

Diebold and Yilmaz (2015) recently introduced variance decomposition networks as tools for quantifying and ranking the systemic risk of individual firms. The nature of these networks and their implied rankings depend on the choice decomposition method. The standard choice is the order invariant generalized forecast error variance decomposition of Pesaran and Shin (1998). The shares of the forecast error variation, however, do not add to unity, making difficult to compare risk ratings and risks contributions at two different points in time. As a solution, this paper suggests using the Lanne-Nyberg (2016) decomposition, which shares the order invariance property. To illustrate the differences between both decomposition methods, I analyzed the global financial system during 2001 – 2016. The analysis shows that different decomposition methods yield substantially different systemic risk and vulnerability rankings. This suggests caution is warranted when using rankings and risk contributions for guiding financial regulation and economic policy.

Subject: Banking, Commercial banks, Econometric analysis, Financial institutions, Financial sector policy and analysis, Insurance, Insurance companies, Systemic risk, Vector autoregression

Keywords: Africa, Asia and Pacific, BEJNG Co., Casualty company Ltd, Commercial banks, Erie indemnity Co, Global, Global financial system, Insurance, Insurance companies, Insurance company, Interconnectedness, Life insurance, Networks, Partial correlation, Regularization techniques, SCOR SE, SHINKONG insurance co Ltd, State bank, Systemic risk, VAR, Variance decomposition, Vector autoregression, Wells fargo, WP

Publication Details

Pages:

48
Volume:

---
DOI:

---
Issue:

---
Series:

Working Paper No. 2017/107
Stock No:

WPIEA2017107
ISBN:

9781475598407
ISSN:

1018-5941

FACTSHEETS

RESOURCES

TOPICS

Flagship Publications

Other Publications

IMF reports and publications by country

Regional Offices

All News

See Also

For Journalists

Press Center

RESOURCES

FLAGSHIPS

KEY SERIES

IMF NOTES

IMF Working Papers