Wrong-Way Risk – Correlation Coefficient Calibration

Informační bulletin České statistické společnosti, 1–2/2015

10 Pages Posted: 28 Apr 2015

See all articles by Jakub Cerny

Jakub Cerny

Charles University in Prague - Faculty of Mathematics and Physics

Jiri Witzany

University of Economics in Prague

Date Written: November 12, 2014

Abstract

Under the new Basel III banking regulation banks should include wrong-way risk (WWR) into the calculation of the credit valuation adjustment (CVA) of the OTC derivatives. WWR takes place when the exposure to a counterparty is adversely correlated with the credit quality of that counterparty. Assuming a link between the interest rate swap (IRS), i.e. financial derivative in which two counterparties repeatedly exchange cash flows based on interest rate value and that the default time is represented by a Gaussian copula with a constant correlation coefficient, the WWR is expressed by this correlation coefficient. Because the observation of the default time means bankruptcy of the company, the correlation cannot be simply estimated using the observed data in contrast to the credit default swap (CDS) rate which is related to the intensity of default. Based on available daily Czech Republic government IRS and CDS rates we estimated the correlation using maximum likelihood method assuming that the systematic factor is governed by the AR(1) process, so we can decorrelate (eliminate autocorrelation) both time series. The results show that the correlation calibrated on the daily data is relatively high, and therefore the WWR should not be neglected in this case.

Keywords: Wrong-way risk, WWR, correlation coefficient calibration, maximum likelihood estimation, CVA

JEL Classification: G20, G28, C51

Suggested Citation

Cerny, Jakub and Witzany, Jiri, Wrong-Way Risk – Correlation Coefficient Calibration (November 12, 2014). Informační bulletin České statistické společnosti, 1–2/2015. Available at SSRN: https://ssrn.com/abstract=2599427 or http://dx.doi.org/10.2139/ssrn.2599427

Jakub Cerny

Charles University in Prague - Faculty of Mathematics and Physics ( email )

Sokolovska 83
Prague, 186 75
Czech Republic

Jiri Witzany (Contact Author)

University of Economics in Prague ( email )

Winston Churchilla Sq. 4
Prague 3, 130 67
Czech Republic

Register to save articles to
your library

Register

Paper statistics

Downloads
160
Abstract Views
691
rank
185,256
PlumX Metrics