It is extremely important to model the empirical distributions of dry bulk\nshipping returns accurately in estimating risk measures. Based on several\ncommonly used distributions and alternative distributions, this paper establishes\nnine different risk models to forecast the Value-at-Risk (VaR) of dry\nbulk shipping markets. Several backtests are explored to compare the accuracy\nof VaR forecasting. The empirical results indicate the risk models based on\ncommonly used distributions have relatively poor performance, while the alternative\ndistributions, i.e. Skewed Student-T (SST) distribution, Skewed Generalized\nError Distribution (SGED), and Hyperbolic distribution (HYP)\nproduce more accurate VaR measurement. The empirical results suggest risk\nmanagers further consider more flexible empirical distributions when managing\nextreme risks in dry bulk shipping markets.
Loading....