Hedge fund pricing and model uncertainty

The performance of hedge funds and mutual funds in emerging markets

“…The first is to screen many variables through stepwise regression techniques (see, e.g., Liang, 1999;Agarwal and Naik, 2004;Vrontos et al, 2008, in a hedge fund context), which usually leads to a relatively high in-sample R 2 , but to a relatively low out-of-sample R 2 . The second option is to select a short list of variables that are assumed to be economically relevant.…”

Detecting structural breaks and identifying risk factors in hedge fund returns: A Bayesian approach

“…Our evaluation of the models is carried out by conducting standard t-tests and Wilcoxon signedrank tests to investigate if the mean and median returns of the replicating portfolios are statistically different from the realized returns (see Agarwal and Naik, 2004). In addition, we use the logarithmic scoring rule which is based on the calculation of the conditional predictive ordinates (see Vrontos et al, 2008).…”

“…The complexity of hedge fund strategies exposes their portfolios to a plethora of economic risk factors and raises the possibility of model misspecification, since there exists no generally accepted model (Vrontos et al, 2008). On the other hand, due to the special features of hedge funds, their return-generating process may exhibit a high degree of non-normality, fat tails and skewness (Amin and Kat, 2003;Kouwenberg and Ziemba, 2007) and be characterized by nonlinearities (Fung and Hsieh, 2004).…”

“…They can also capture nonlinearities and changes in the variance across time; assuming different segment-specific variances is an alternative way of modeling time-varying volatilities, rather than modeling the volatility directly (for example, using GARCH models as in Giamouridis and Vrontos, 2007;Vrontos et al, 2008). In this study we aim at detecting the presence of multiple structural breaks in hedge fund return series and at inferring their number and their positions.…”

Hedge funds and optimal asset allocation: Bayesian expectations and spanning tests

“…For instance, Bayesian model averaging is used to account for model uncertainty regarding the relevant risk factors explaining hedge fund returns(Vrontos et al 2008;Giannikis and Vrontos 2011) whileCvi- tanic et al (2003) consider the uncertainty regarding hedge fund managers' ability to generate positive abnormal returns.…”