Do hedge funds deliver alpha? A Bayesian and bootstrap analysis

• 成果类型: Article
• 署名作者: Kosowski, Robert; Naik, Narayan Y.; Teo, Melvyn
• 署名单位: University of London; London Business School; Imperial College London; Singapore Management University
• 刊物名称: JOURNAL OF FINANCIAL ECONOMICS
• ISSN/ISSBN: 0304-405X
• DOI: 10.1016/j.jfineco.2005.12.009
• 发表日期: 2007
• 页码: 229-264
• 关键词: hedge fund performance; persistence; alpha; factor models; Bayesian; bootstrap

摘要

Using a robust bootstrap procedure, we find that top hedge fund performance cannot be explained by luck, and hedge fund performance persists at annual horizons. Moreover, we show that Bayesian measures, which help overcome the short-sample problem inherent in hedge fund returns, lead to superior performance predictability. Sorting on Bayesian alphas, relative to OLS alphas, yields a 5.5% per year increase in the alpha of the spread between the top and bottom hedge fund deciles. Our results are robust and relevant to investors as they are neither confined to small funds, nor driven by incubation bias, backfill bias, or serial correlation. (c) 2006 Elsevier B.V. All rights reserved.