Portfolio selection using hierarchical Bayesian analysis and MCMC methods

“…Within this framework we rely on our beliefs or prior information about the parameters of the model and formalize these beliefs in form of prior distributions. The most frequently applied priors for µ and Σ in the financial literature are the diffuse prior (see, e.g., Barry (1974), Brown (1976), and Klein and Bawa (1976)), the conjugate prior (Frost and Savarino (1986)), and the hierarchical prior (Greyserman et al (2006)) which we introduce next. The diffuse prior is an uninformative prior, which implies that the statistician has no additional information about the stochastic nature of the unknown parameters.…”

Section: Bayesian Vs Frequentist Portfolio Selectionmentioning

confidence: 99%

“…Next, we consider the hierarchial Bayes model which was suggested by Greyserman et al (2006). They demonstrated that a fully hierarchical Bayes procedure produces promising results warranting more study.…”

Section: Hierarchical Priormentioning

confidence: 99%

“…The sample size n is set to 50, which is a typical value in financial literature and corresponds to roughly two months of daily data or a year of weekly data, respectively. In all considered cases we take the following parameters for the conjugate prior ν c = κ c = n, µ c = 0 k and S c = I k ; for the hierarchial prior 1 = 0.0001, 2 = 0.0001 (as in Greyserman et al (2006)), κ h = ν h = n and S h = I k ; for the informative prior δ 1 = 1 and δ 2 = 0.5, ν I = n, w I = 1/k, S I = 1.…”

Section: Numerical Studymentioning

confidence: 99%

See 1 more Smart Citation

Bayesian estimation of the global minimum variance portfolio

Bodnar

Mazur

Okhrin

2017

European Journal of Operational Research

View full text Add to dashboard Cite

In this paper we consider the estimation of the weights of optimal portfolios from the Bayesian point of view under the assumption that the conditional distribution of the logarithmic returns is normal. Using the standard priors for the mean vector and the covariance matrix, we derive the posterior distributions for the weights of the global minimum variance portfolio. Moreover, we reparameterize the model to allow informative and non-informative priors directly for the weights of the global minimum variance portfolio. The posterior distributions of the portfolio weights are derived in explicit form for almost all models. The models are compared by using the coverage probabilities of credible intervals.In an empirical study we analyze the posterior densities of the weights of an international portfolio.

show abstract

“…Nevertheless, if the gain in the performance does not cover the extra transaction costs, less accurate, but less variable weighting strategies would be preferred. To study this issue we define portfolio turnover as in Greyserman et al (2006), that is the sum of the absolute changes in the portfolio weights from the previous month to that month. This metric intuitively represents the fraction of the portfolio value that has to be liquidated/reallocated at the point of rebalancing.…”

Section: Traditional Allocation Approachesmentioning

confidence: 99%

Portfolio Allocation of Hedge Funds

Bruder¹,

Darolles

Koudiraty³

et al. 2011

SSRN Journal

View full text Add to dashboard Cite

Research in hedge fund investing proposes different solutions to build optimal hedge fund portfolios. However, these solutions are direct extensions of the usual meanvariance framework, and still suffer from model risks. More complex approaches start to be used but are related to numerous estimation risk s. We compare in this paper the out-sample properties of different allocation models through a dynamic investment exercise using hedge fund indices. We show that the best out-of-sample properties are obtained by allocation models that take into account the specific statistical properties of hedge fund returns.

show abstract

Portfolio selection using hierarchical Bayesian analysis and MCMC methods

Cited by 34 publications

References 25 publications

Hedge fund portfolio construction: A comparison of static and dynamic approaches

Hedge fund portfolio construction: A comparison of static and dynamic approaches

Bayesian estimation of the global minimum variance portfolio

Portfolio Allocation of Hedge Funds

Contact Info

Product

Resources

About