A Broad-Spectrum Computational Approach for Market Efficiency

Olivier Brandouy () and Philippe Mathieu
Additional contact information
Philippe Mathieu: LIFL, UMR CNRS-USTL 8022, France

No 492, Computing in Economics and Finance 2006 from Society for Computational Economics

Abstract: The Efficient Market Hypothesis (EMH) is one of the most investigated questions in Finance. Nevertheless, it is still a puzzle, despite the enormous amount of research it has provoked. For instance, it is still discussed that market cannot be outperformed in the long run (Detry and Gregoire, 2001), persistent market anomalies cannot be easily explained in this theoretical framework (Shiller, 2003) and some talented hedge-fund managers keep earning excess risk-adjusted rates of returns regularly. We concentrate in this paper on the weak form of efficiency(Fama, 1970). We focus on the efficacity of simple technical trading rules, following a large research stream presented in Park and Irwin (2004). Nevertheless, we depart from previous works in many ways : we first have a large population of technical investment rules (more than 260.000) exploiting real-world data to manage a financial portfolio. Very few researches have used such a large amount of calculus to examine the EMH. Our experimental design allows for strategy selection based on past absolute performance. We take into account the data-snooping risk, which is an unavoidable problem in such broad-spectrum researches, using a rigorous Bootstrap Reality Check procedure. While market inefficiencies, after including transaction costs, cannot clearly be successfully exploited, our experiments present troubling outcomes inviting close re-consideration of the weak-form EMH.

Keywords: efficient market hypothesis; large scale simulations; bootstrap (search for similar items in EconPapers)
JEL-codes: G14 C63 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-cmp, nep-ets and nep-fin
Date: 2006-07-04
View list of references

Downloads: (external link)
http://repec.org/sce2006/up.8772.1141586971.pdf (application/pdf)

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: http://EconPapers.repec.org/RePEc:sce:scecfa:492

Access Statistics for this paper

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