Extreme Unconditional Dependence Vs. Multivariate GARCH Effect in the Analysis of Dependence Between High Losses on Polish and German Stock Indexes

Abstract

Classical portfolio diversification methods do not take account of any dependence between extreme returns (losses). Many researchers provide, however, some empirical evidence for various assets that extreme-losses co-occur. If the co-occurrence is frequent enough to be statistically significant, it may seriously influence portfolio risk. Such effects may result from a few different properties of financial time series, like for instance: (1) extreme dependence in a (long-term) unconditional distribution, (2) extreme dependence in subsequent conditional distributions, (3) time-varying conditional covariance, (4) time-varying (long-term) unconditional covariance, (5) market contagion. Moreover, a mix of these properties may be present in return time series. Modeling each of them requires different approaches. It seams reasonable to investigate whether distinguishing between the properties is highly significant for portfolio risk measurement. If it is, identifying the effect responsible for high loss co-occurrence would be of a great importance. If it is not, the best solution would be selecting the easiest-to-apply model. This article concentrates on two of the aforementioned properties: extreme dependence (in a long-term unconditional distribution) and time-varying conditional covariance.