Value-at-risk estimation with multivariate garch models |
Value-at-Risk (VaR) method has been accepted globally by both risk managers and regulators as a tool to identify and control exposure to financial market risk. Basel II regulation employs VaR methodology for capital requirements calculations for the market risks to which commercial banks are exposed. The goal of this paper is to implement the multivariate GARCH (mGARCH) methodology as the internal VaR model for market risk measurement in Serbian commercial banks. Assuming Normal and Student-t distribution of the returns the parameters for orthogonal mGARCH and CCC-mGARCH VaR models are estimated for each of 250 consecutive days, for the hypothetical trading portfolio, by employing maximum likelihood method. The level of capital requirements are calculated for corresponding VaR methods and validation is done by applying Basel II and Kupiec test.
Nebojša Nikolić, Vesna Manojlović |