Optimal Hedge Fund Allocations

Should investors include commodities in their portfolios after all? New evidence

“…On the other hand, the joint CDF needs to be estimated; this requires assuming either a specific estimator or a parametric form for the CDF leading to an estimation error. To circumvent this, we estimate optimal portfolios by applying the full scale optimization method proposed by Cremers et al (2005) and Adler and Kritzman (2007). This is a non-parametric technique based on a numerical grid search procedure that uses as many asset mixes as necessary to identify the weights that yield the highest expected utility.…”

“…Third, we construct optimal portfolios by taking into account the higher order moments of the returns distributions of the involved assets. To this end, direct utility maximization is performed (e.g., Cremers et al, 2005;Adler and Kritzman, 2007). The appeal of this approach compared to the MV optimization applied by previous studies is that it yields optimal portfolios by maximizing the expected utility of the investor for any assumed type of returns distribution and description of her preferences.…”

In Defense of Optimization: The Fallacy of 1/N

“…Moreover, it allows for any description of investor preferences. It thus yields the truly optimal portfolio in sample, whereas mean-variance optimization provides an approximation of the in-sample truth (Cremers, Kritzman, and Page 2005;Sharpe 2007). Adler and Kritzman (2007) showed that full-scale optimization outperforms mean-variance optimization out of sample as well.…”

Stock portfolio selection with full-scale optimization and differential evolution

“…Cremers et al (2005) and Adler and Kritzman (2007) introduced the technique and demonstrated that it is useful for hedge fund selection. Hagstro¨mer et al (2008) showed that it also is useful for choice between equity indices and that this is robust for several different utility function specifications.…”