In this paper we address how to evaluate tail risk forecasts for systemic risk measurement. We propose two loss functions, the Tail Tick Loss and the Tail Mean Square Error, to evaluate, respectively, CoVaR and MES forecasts. We then analyse CoVaR and MES forecasts for a panel of top US financial institutions between 2000 and 2012 constructed using a set of bivariate DCC-GARCH-type models. The empirical results highlight the importance of using an appropriate loss function for the evaluation of such forecasts. Among other findings, the analysis confirms that the DCC-GJR specification provides accurate predictions for both CoVaR and MES, in particular for the riskiest group of institutions in the panel (Broker-Dealers).

BROWNLEES, C., CAVALIERE, G., MONTI, A. (2018). EVALUATING THE ACCURACY OF TAIL RISK FORECASTS FOR SYSTEMIC RISK MEASUREMENT. ANNALS OF FINANCIAL ECONOMICS, 13(02), 1-28 [10.1142/S2010495218500094].

EVALUATING THE ACCURACY OF TAIL RISK FORECASTS FOR SYSTEMIC RISK MEASUREMENT

BROWNLEES, CHRISTIAN-TIMOTHY;CAVALIERE, GIUSEPPE
;
MONTI, ALICE
2018

Abstract

In this paper we address how to evaluate tail risk forecasts for systemic risk measurement. We propose two loss functions, the Tail Tick Loss and the Tail Mean Square Error, to evaluate, respectively, CoVaR and MES forecasts. We then analyse CoVaR and MES forecasts for a panel of top US financial institutions between 2000 and 2012 constructed using a set of bivariate DCC-GARCH-type models. The empirical results highlight the importance of using an appropriate loss function for the evaluation of such forecasts. Among other findings, the analysis confirms that the DCC-GJR specification provides accurate predictions for both CoVaR and MES, in particular for the riskiest group of institutions in the panel (Broker-Dealers).
2018
BROWNLEES, C., CAVALIERE, G., MONTI, A. (2018). EVALUATING THE ACCURACY OF TAIL RISK FORECASTS FOR SYSTEMIC RISK MEASUREMENT. ANNALS OF FINANCIAL ECONOMICS, 13(02), 1-28 [10.1142/S2010495218500094].
BROWNLEES, CHRISTIAN; CAVALIERE, GIUSEPPE; MONTI, ALICE
File in questo prodotto:
File Dimensione Formato  
Evaluating Post print.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione - Non commerciale (CCBYNC)
Dimensione 359.42 kB
Formato Adobe PDF
359.42 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/672121
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? 4
social impact