Integrating Liquidity Risk in a Parametric Intraday VaR Framework

(eng) Value at Risk (VaR) became, during the last few years, one of the most popular tools for measuring market risk across financial institutions. Mostly used on an interday basis, VaR suffers from several drawbacks. Among these, there is the fact that only one observation is used to characterize the activity of the entire day. The integration of the intraday information becomes then a necessity. Moreover, classical VaR modelling often ignores the presence of a liquidity component. This liquidity component arises from the market-to-market hypothesis which states that the theoretical setting off implied by the VaR calculation occurs at the mid price. Most of the time, this settlement price is lower and depends mainly on the market depth and the level of the quoted spread. Following the model initiated by Bangie et al. (1999), this article presents a new framework for integrating liquidity risk into a standard parametric VaR.