Research Articles

Predicting Hedge Fund Failure: A Comparison of Risk Measures

Bing Lianga1 and Hyuna Parka2

a1 Isenberg School of Management, University of Massachusetts at Amherst, 121 Presidents Dr., Amherst, MA 01003.

a2 College of Business, Minnesota State University Mankato, 150 Morris Hall, Mankato, MN 56001.


This paper compares downside risk measures that incorporate higher return moments with traditional risk measures such as standard deviation in predicting hedge fund failure. When controlling for investment strategies, performance, fund age, size, lockup, high-water mark, and leverage, we find that funds with larger downside risk have a higher hazard rate. However, standard deviation loses the explanatory power once the other explanatory variables are included in the hazard model. Further, we find that liquidation does not necessarily mean failure in the hedge fund industry. By reexamining the attrition rate, we show that the real failure rate of 3.1% is lower than the attrition rate of 8.7% on an annual basis during the period of 1995–2004.


We thank Gordon Alexander (the referee), Thomas Berry-Stölzle, Stephen Brown, Mila Getmansky, Hossein Kazemi, Paul Malatesta (the editor), Felix Meschke, Bernard J. Morzuch, Joseph Reising, and seminar participants at the 2006 FMA annual meeting, the University of Colorado, University of Massachusetts at Amherst, Koç University, Minnesota State University Mankato, and the Society of Quantitative Analysts for helpful comments. All remaining errors are our own.