Causal dependency in extreme returns
AbstractModelling of extreme price movements is one of the greatest challenges to risk managers. Extreme Value Theory provides useful and natural tools to analyze a distribution of such events but they are unable to predict the future behavior of extreme returns and their consequences. On the other hand we know that the sequence of extrema behavior, similar to volatility, exhibits long term memory. We have foundnew property of that sequence on the capital markets, what could be useful in construction of a predictive model of extrema. We argue that in the blocks of returns shorter than quarterly, returns maxima cause minima but it is not a common inverse causal dependency.
|Publication size in sheets||0.55|
|Book||Jedlička Pavel (eds.): Hradec Economic Days. Double-blind peer-reviewed proceedings part IV. of the International Scientific Conference Hradec Economic Days 2015, Hradec Economic Days, vol. 5, no. 4, 2015, University of Hradec Králové, ISBN 978-80-7435-549-3, 375 p.|
|Keywords in English||extreme returns, cross-correlation, Granger causality, extreme value theory|
|Score|| = 15.0, 12-02-2020, BookChapterSeriesAndMatConfByIndicator|
= 15.0, 12-02-2020, BookChapterSeriesAndMatConfByIndicator
|Publication indicators||= 0|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.