Paper
Journal of Derivatives & Hedge Funds (2008) 14, 9–30. doi:10.1057/jdhf.2008.3
On comparing hedge fund strategies using new Hausman-based estimators
Practical applications In order to correct specification errors in financial models of returns, the authors propose new procedures to generate strong instruments based on higher moments and cumulants of the explanatory variables. By doing so, we rehabilitate a well-known estimator, the Generalized Method of Moments (GMM), which uses these innovative instruments and we thus construct our new estimators, called the GMM-C and the GMM-hm. A new indicator is also developed for gauging measurements errors in financial models of hedge fund returns and it appears quite promising for the financial practitioner.
François-Éric Racicot1 and Raymond Théoret2
Correspondence: François-Éric Racicot, Department of Administrative Sciences, University of Quebec (Outaouais), (UQO), 101 St-Jean-Bosco Street, Gatineau (Hull), Quebec J8X 3X7, Canada. Tel: +1 819 595-3900 ext. 1727, Fax: +1 819 773 1797, E-mail: francoiseric.racicot@uqo.ca
1François-Éric Racicot PhD, is Associate Professor of Finance at the Department of Administrative Sciences, University of Quebec - Outaouais (LQO). His research interests focus on the problems of measurement errors and specification errors in financial models of returns. He is also interested in developing new methods used for forecasting financial time series.
2Raymond Théoret PhD, is Professor of Finance at the Department of Finance, University of Quebec - Montreal (UQAM). His research focuses on the volatility of bank income in relation with stock market performance, self-enforcing labour contracts and problems of measurement errors in financial models.
Received 4 March 2008; Revised 4 March 2008.
Abstract
This paper proposes new Hausman-based estimators lying on higher moments and cumulants. Our study gives way to a new indicator signalling the presence of specification errors in financial models. We apply our battery of tests to a sample of 21 HFR hedge funds strategies over the period 1990–2005. Our tests reveal that it is much more preferable to account for specification errors when estimating financial models of returns. Actually, the performance ranking of hedge funds strategies may change significantly when accounting for specification errors.
Keywords:
hedge fund returns, alpha of Jensen, financial models, cumulants, higher moments, specification errors, aggregation bias, Hausman-C, GMM-C
