Multiple-day VaR calculating rules in financial risk management

In financial risk management, the Value-at-Risk (VaR) is a commonly used measure of asset´s short period market risk. General external risk indicator for multiple-day VaR, proposed by The Basel Committee on Banking Supervision (1996, 2003), is the square-root-of-time (SQRT) rule which is derived based on the Gaussian return assumption. Danielsson and Vries (1997), Dacorogna, Muller, Pictet and Vries (2001) pointed out the risks and drawbacks by using the SQRT rule and proposed a-root rule which is derived from the heavy-tailed distributions. In this paper, the authors derive and conduct a research on a scaling rule based on some more generalized tail which also has heavier tail than Gaussian. An example by using the property of Normal Inverse Gaussian distribution which is called NIG rule is shown to be a more stable indicator to regulate market risk for external risk regulators. The results of numerical calculation with nancial data are described and a comparative study by using all three rules are included. It is expected the research undertaken on scaling rules and its realization can provide practical reference to nancial risk supervision departments.