Parametric and Nonparametric VaR Daily Returns Estimation

  • Vladimir Dj. Djakovic University of Novi Sad, Faculty of Technical Sciences, Trg Dositeja Obradovica 6, 21000 Novi Sad
  • Goran B. Andjelic Educons University, Faculty of Business Economy, Vojvode Putnika 87, 21208 Sremska Kamenica
  • Isidora Lj. Ljumovic Economics Institute, Kralja Milana 16, 11000 Belgrade
Keywords: Risk, Historical Simulation, Delta normal VaR, Extreme Value Theory, Investment, Value at Risk, VAR model,

Abstract


Taking into account current trends and opportunities in the transitional markets, the subject of the research is to analyze and quantify the different Value at Risk (VaR) calculation models in the light of investment risk assessment performance in the domestic market. The research objective is to gain a series of qualitative and quantitative information about the possibilities of effective application of different VaR models in investment decision-making in order to minimize risks of investment activities. The research focuses on the domestic financial market and covers the period 2006-2012. The research methodology involves the use of MANOVA analysis, discriminant analysis, and Roy's test, and is adapted to the specific characteristics of the transitional market of the Republic of Serbia. The research results confirm the prominent place, role and importance of different VaR models in the light of the investment risk quantification in the domestic market, with reference to the specificities between particular VaR models. In this sense, the results will be useful both for academic and professional communities, in the context of the successful application of different VaR models in decision-making about investment activities.
Published
2014/12/24
Section
Original Scientific Paper