Journal of Risk Model Validation

Risk.net

Downside risk measure performance in the presence of breaks in volatility

Johannes Rohde

  • The comparison of Value at Risk and Expected Shortfall regarding their sensitivity to structural breaks in the volatility using a loss function framework indicate predominance of Expected Shortfall over Value at Risk.
  • These results are confirmed within an empirical application using several stock indices for the estimated models.
  • The work supports the findings of prior research regarding the properties of VaR and ES.

ABSTRACT

The accurate evaluation of a risk measure employed by a financial institution is of high importance in view of that institution's minimum capital requirement. Having a sensitive reaction to breaks in the volatility of the profit-and-loss process is a desirable property of the underlying measure. This paper proposes a loss function-based framework for the comparative measurement of the sensitivity of quantile downside risk measures to breaks in volatility or distribution. We do this by extending the model comparison approach introduced by Lopez in 1998. Value-at-risk and expected shortfall (ES) are contrasted over realistic evaluation horizons within a broad simulation study, in which numerous settings involving volatility breaks of different intensities and several data-generating processes are checked by employing a magnitude-type loss function. As a result, it can generally be noted that ES appears to be the superior measure in terms of its ability to identify breaks in the volatility. In addition, an empirical study, in which data from six stock market indexes are used, demonstrates the applicability of this procedure and reconfirms the findings from the simulation study.

To continue reading...

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an indvidual account here: