Boolell-Gunesh S., Broihanne M-H., Merli M.
This paper analyses the disposition effect at an individual level by studying the trading records of 20 379 investors over 1999-2006. As in previous studies, we confirm a huge heterogeneity among investors and we propose to explain these differences on the basis of financial sophistication and trading behavior proxies. In our new approach, we use direct sophistication variables: trading of foreign assets, derivative assets and bonds as well as trading on both tax-free and traditional accounts. We show that these variables significantly reduce the level of the disposition effect. Furthermore, based on a dynamic panel data analysis, we question investors’ ability to correct their bias over time. Results show that individual investors’ disposition effect decreases over time and that this decrease is partly caused by sophistication variables.Download
This paper reviews the literature on Hedge Fund performance attribution. Hedge Funds follow very dynamic and leveraged strategies and invest massively in derivatives and illiquid securities. Consequently, these funds present linear but also non-linear relationships with market indexes. The article investigates the risk factors that have been used to capture the linear and non-linear comovements of Hedge Fund returns with passive indexes. The review especially discusses the significance of adding option-like or distribution-based factors to benchmark models. It moreover supports the evidence that multi-moment risk premiums could considerably improve the models traditionally used to evaluate Hedge Funds.Download
E-I. Dumitrescu, C. Hurlin, V. Pham
In this paper we propose a new tool for backtesting that examines the quality of Value-at-Risk (VaR) forecasts. To date, the most distinguished regression-based backtest, proposed by Engle and Manganelli (2004), relies on a linear model. However, in view of the dichotomic character of the series of violations, a non-linear model seems more appropriate. In this paper we thus propose a new tool for backtesting (denoted DB) based on a dynamic binary regression model. Our discrete-choice model, e.g. Probit, Logit, links the sequence of violations to a set of explanatory variables including the lagged VaR and the lagged violations in particular. It allows us to separately test the unconditional coverage, the independence and the conditional coverage hypotheses and it is easy to implement. Monte-Carlo experiments show that the DB test exhibits good small sample properties in realistic sample settings (5% coverage rate with estimation risk). An application on a portfolio composed of three assets included in the CAC40 market index is finally proposed.Download