New Working Paper: Tracking Hedge Funds Using Linear Models
The working paper “ Tracking Hedge Funds Using Linear Models” by Kay Eichhorn-Schott, Margherita Giuzio, Sandra Paterlini and Vincent Weber has been posted on-line at ssrn archive:
Whether hedge fund returns could be attributed to systematic risk exposures rather than managerial skills is an interesting debate among academics and practitioners. Recent literature suggests that hedge fund performance is mostly determined by alternative betas, which justifies the construction of investable hedge fund clones or replicators. In this paper, we first study the risk exposure of different hedge fund indices to a set of liquid asset class factors by means of a Sharpe style analysis. Then, we propose a LASSO regression framework based on the l1-norm penalty to model and replicate hedge fund returns. We evaluate the performance of the hedge fund clones in terms of tracking ability, turnover and sparsity and find that LASSO clones are able to closely track the hedge fund indices with a low number of non-zero weights and low turnover.