Metodologías de estimación del valor en riesgo (VaR) : índice Nasdaq compuesto bajo, métodos paramétricos, no paramétricos y de valor extremo

Abstract

Value-at-Risk (VaR) is a measure of market risk that aims to establish the upper limit of possible losses in the value of an asset or portfolio of assets, under a previously defined confidence level. Nowadays there are different approaches to estimate this measure such as parametric methods, non-parametric methods and Extreme Value Theory (EVT). This research does a comparison between estimations made using the Historical Simulation, Variance-Covariance, Extreme Value Theory, and Volatility Adjusted methods. The results obtained show that the Volatility Adjusted VaR model proposed by Hull & White (1998) has the best fit in high-volatility time periods. While EVT VaR shows the best fit on normal time periods for very high confidence levels.