A new method for estimating value at risk with EVT and HS

During the past decade, Value at Risk (VaR) has become one of most commonly used Tools in risk measurement. In this paper, We propose a new method for estimating VaR. Our approach combines HS method to estimate the interior and the extreme value theory to estimate the tails. This paper uses a sample of the returns of S&P 500 daily closing index to test the performance of our VaR procedure. This approach is also backtested for financial data at different confidence level. The results of the backtesting indicate that the new approach is an adequate risk measure.