Deviation from normality and Sharpe ratio behavior: a brief simulation study

Abstract : Sharpe ratio has been widely used in the portfolio management industry as well as fund industry (Robertson, 2001; Scholz and Wilkens, 2005). Users often forget the main core assumption describing the appropriateness of such a riskadjusted performance measure, namely asset return normality. This concern is of huge significance insofar as performanceindicators drive the asset allocation policy, performance forecasts and cost of capital assessment among others (Farinelli et al., 2008; Lien, 2002; Christensen and Platen, 2007). We employ a brief simulation study to assess the impact of deviations from normality on the performance measures and rankings inferred from Sharpe ratio's estimates. Our analysis allows for assessing the possible bias in both performance measurement and ranking, which results from the existence and the magnitude of skewness and kurtosis patterns in asset returns. This study proposes a method to extract an unbiased performance measure (i.e. unbiased Sharpe ratios) from observed classic Sharpe ratios after accounting for the returns' skewness bias. The resulting unbiased Sharpe ratio outperforms its classic counterpart at the stock picking level.
Type de document :
Article dans une revue
Investment Management and Financial Innovations, 2010, vol.7 (n°4), pp.106-118
Liste complète des métadonnées

https://hal-rbs.archives-ouvertes.fr/hal-00568613
Contributeur : Emilie Breton <>
Soumis le : mercredi 23 février 2011 - 11:01:42
Dernière modification le : lundi 18 mai 2015 - 12:55:11

Identifiants

  • HAL Id : hal-00568613, version 1

Collections

Citation

Hayette Gatfaoui. Deviation from normality and Sharpe ratio behavior: a brief simulation study. Investment Management and Financial Innovations, 2010, vol.7 (n°4), pp.106-118. 〈hal-00568613〉

Partager

Métriques

Consultations de la notice

201