Measuring model risk in the European energy exchange

It has been shown that model risk has an important effect on any risk measurement procedures, hence its proper quantification is becoming crucial especially in energy markets, where market participants face several kinds of risks (such as volumetric, liquidity, and operational risk). Therefore, relaxing the assumption of normality and using a wide range of alternative distributions, we quantify the model risk in the German wholesale electricity market (the European Energy Exchange, EEX) by studying day–ahead electricity prices from 2001 to 2013 using the well-established setting of GARCH–type models. Taking advantage of this long price history, we investigate the “time evolution” of the measured model risk across years by adopting a rolling window procedure. Our results confirm that the increasing complexity of energy markets has affected the stochastic nature of electricity prices which have become progressively less normal through years, hence resulting in an increased model risk.