A0239
Title: Detecting changes in the strength of dependence between financial data sets
Authors: Alexander Schnurr - University Siegen (Germany) [presenting]
Abstract: The concept of ordinal pattern dependence is recalled between time series and shows in an explorative study that both types of this dependence show up in real world financial data. The classical way to capture the leverage effect in models for stock markets is to assume a negative correlation between the two datasets, which is constant in time. However, there is strong evidence that this effect is not constant but evolves over time. It seems that there are periods where the effect is weaker, and sometimes, it even seems to be turned around. Taking these empirical findings into account, more sophisticated models were suggested. The correlation structure was modeled by a deterministic function, was made state space dependent or even modeled itself by a stochastic process. Instead of proposing more complicated models, a rather simple approach is introduced to analyze whether there is a dependence structure between two datasets: In order to capture the zigzag of datasets, so-called ordinal patterns are used. From this point of view, the two datasets are compared. On some occasions, as an example, the S\&P 500 and the VIX are considered; a dependence structure of this kind seems to be more likely to be found in real data than the dependence modeled by the classical approach via correlation.
