CMStatistics 2017: Start Registration
View Submission - CFE
A1755
Title: Low volatility of alternative UCITS: Fact or fiction Authors:  Nabil Bouamara - UCLouvain (Belgium) [presenting]
Kris Boudt - Vrije Universiteit Brussel and VU Amsterdam (Belgium)
David Ardia - HEC Montréal (Canada)
Abstract: The (il)liquidity of alternative investments is attracting much attention from investors and regulators. However, from the viewpoint of fund structures this is a hard concept to define and measure. To overcome this problem, it has been previously establishes the classical connection between liquidity and autocorrelation for fund structures and showed that smoothed returns (due to pricing ambiguity) may give a deflated view of the true volatility of underlying returns. The model is based on a finite moving average model under a summation constraint and implicitly assumes bounded parameters. Within this framework, the maximum likelihood estimator is prone to estimation error. We provide a methodological and financial research contribution in terms of modelling the parameter structure and propose a structured estimation approach. Contrary to the standard unconditional model, we use commonality explained by fund characteristics and a nearest moment estimation. Finally, we illustrate the methods usefulness on a set of regulated liquid alternatives.