Statistical Analysis of Hedge Fund Returns: Replication and Nonlinearities
<-- Return to the list
Date: 09-10-2007
Start Time:
6:00pm
End Time: 7:30pm
Speaker: Raphael Douady of Riskdata
Location: 412 Schapiro CEPSR, Davis Auditorium
ABSTRACT
In just a few years, hedge funds have reached such an importance in the investment landscape that they now bear a significant amount of risk in the global financial investment industry. Although apparently uncorrelated, they occasionally react as a herd in front of certain market movements, like if they were selling some put options. More recently, several banks started proposing investment vehicles that are supposed “replicate” hedge fund returns with lower fees. This talk will be devoted to analysing hedge fund returns and identifying relevant statistical models. One of the important findings is the poor quality of usual multilinear, non-dynamic models and the necessity to use nonlinear as well as dynamic models on order to get a chance to get a looking forward risk profiling of hedge funds. We also show that using such models allows, in many cases, to uncover the most important aspects of the trading strategy without specifically knowing anything about holdings, thus anticipating the behaviour of portfolios of hedge funds.
BIO
Raphael Douady is one of the founders of Riskdata, the market-leading provider of risk management tools for investors, asset managers, hedge funds and funds of funds. With ten years experience in the banking industry (risk management, option models, trading strategies) and twenty years research in pure and applied mathematics, Dr Douady is renowned for his highly sophisticated quantitative solutions and statistical analysis. He created and teaches the New York University seminar of Mathematical Finance.