Extreme observations in developed and emerging equity markets

Pilar Grau

No 254, Computing in Economics and Finance 2006 from Society for Computational Economics

Abstract: It is widely accepted that the distribution of financial returns has heavy tails. In this context it is important to understand the frequency and importance of extreme events in financial markets. Extreme Value Theory is the appropriate framework for studying the tail behaviour of a distribution. Tail index estimators, such Hill index can be used to measure the shape of the tail, but it depends for its accuracy on a correct choice of the threshold where the tail begins, and the tail shape estimates are inefficient unless the threshold is accurately determined. We will apply bootstrap methodology to select the correct sample fraction for tail estimation. Also Generalized Pareto Distribution (GPD) model is a convenient framework for the approximation of the threshold exceedances distribution and correct inference depends for its accuracy on a correct choice of the threshold. In this paper we will use corrected threshold selection to explore similarities and differences between tail distributions in equity markets using stock index time series with different characteristics, such as size and maturity. We will try to find out if the probability of extreme events is similar in big or small markets and in mature or emerging markets.

Keywords: Extreme Value Theoy; Bootstrap; Tail index; Emerging Markets (search for similar items in EconPapers)
JEL-codes: C15 G12 (search for similar items in EconPapers)
Date: 2006-07-04
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sce:scecfa:254

Access Statistics for this paper

More papers in Computing in Economics and Finance 2006 from Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Christopher F. Baum ().