Die Quantifizierung von Marktrisiken in der Tierproduktion mittels Value-at-Risk und Extreme-Value-Theory

Abstract

The objective of this paper is to investigate the performance of different Value-at-Risk (VaR) models in the context of risk assessment in hog production. The paper starts with a description of traditional VaR models, i.e. Variance-Covariance-Method (VCM) and Historical Simulation (HS). We address two well known problems, namely the fat tailedness of return distributions and the time aggregation of VaR forecasts. Afterwards, Extreme-Value-Theory (EVT) is introduced in order to overcome these problems. The previously described methods are then used to calculate the VaR of hog production under German market conditions. It turns out that EVT, VCM, and HS lead to different VaR forecasts if the return distributions are fat tailed and if the forecast horizon is long. Finally, we discuss the strengths and weaknesses of these rather new risk management methods thereby trying to identify fields for potential applications in the agribusiness.