Portfolio optimization based on stochastic dominance and empirical likelihood

Gerrit Tjeerd (Thierry) Post, Selçuk Karabatı, Stelios Arvanitis

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This study develops a portfolio optimization method based on the Stochastic Dominance (SD) decision criterion and the Empirical Likelihood (EL) estimation method. SD and EL share a distribution-free assumption framework which allows for dynamic and non-Gaussian multivariate return distributions. The SD/EL method can be implemented using a two-stage procedure which first elicits the implied probabilities using Convex Optimization and subsequently constructs the optimal portfolio using Linear Programming. The solution asymptotically dominates the benchmark and optimizes the goal function in probability, for a class of weakly dependent processes. A Monte Carlo simulation experiment illustrates the improvement in estimation precision using a set of conservative moment conditions about common factors in small samples. In an application to equity industry momentum strategies, SD/EL yields important out-of-sample performance improvements relative to heuristic diversification, Mean–Variance optimization, and a simple ‘plug-in’ approach.

Original languageEnglish
Pages (from-to)167-186
Number of pages20
JournalJournal of Econometrics
Volume206
Issue number1
DOIs
Publication statusPublished - Sep 1 2018

Fingerprint

Stochastic Dominance
Portfolio Optimization
Empirical Likelihood
Convex optimization
Linear programming
Momentum
Two-stage Procedure
Common factor
Optimal Portfolio
Moment Conditions
Likelihood Methods
Distribution-free
Monte Carlo Experiment
Diversification
Equity
Plug-in
Convex Optimization
Small Sample
Simulation Experiment
Optimization Methods

Keywords

  • Empirical likelihood
  • Momentum strategies
  • Portfolio optimization
  • Stochastic dominance

ASJC Scopus subject areas

  • Economics and Econometrics
  • Applied Mathematics

Cite this

Portfolio optimization based on stochastic dominance and empirical likelihood. / Post, Gerrit Tjeerd (Thierry); Karabatı, Selçuk; Arvanitis, Stelios.

In: Journal of Econometrics, Vol. 206, No. 1, 01.09.2018, p. 167-186.

Research output: Contribution to journalArticle

Post, Gerrit Tjeerd (Thierry) ; Karabatı, Selçuk ; Arvanitis, Stelios. / Portfolio optimization based on stochastic dominance and empirical likelihood. In: Journal of Econometrics. 2018 ; Vol. 206, No. 1. pp. 167-186.
@article{44e6a1186cf24f2587812bd5d4fe07d6,
title = "Portfolio optimization based on stochastic dominance and empirical likelihood",
abstract = "This study develops a portfolio optimization method based on the Stochastic Dominance (SD) decision criterion and the Empirical Likelihood (EL) estimation method. SD and EL share a distribution-free assumption framework which allows for dynamic and non-Gaussian multivariate return distributions. The SD/EL method can be implemented using a two-stage procedure which first elicits the implied probabilities using Convex Optimization and subsequently constructs the optimal portfolio using Linear Programming. The solution asymptotically dominates the benchmark and optimizes the goal function in probability, for a class of weakly dependent processes. A Monte Carlo simulation experiment illustrates the improvement in estimation precision using a set of conservative moment conditions about common factors in small samples. In an application to equity industry momentum strategies, SD/EL yields important out-of-sample performance improvements relative to heuristic diversification, Mean–Variance optimization, and a simple ‘plug-in’ approach.",
keywords = "Empirical likelihood, Momentum strategies, Portfolio optimization, Stochastic dominance",
author = "Post, {Gerrit Tjeerd (Thierry)} and Sel{\cc}uk Karabatı and Stelios Arvanitis",
year = "2018",
month = "9",
day = "1",
doi = "10.1016/j.jeconom.2018.01.011",
language = "English",
volume = "206",
pages = "167--186",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Portfolio optimization based on stochastic dominance and empirical likelihood

AU - Post, Gerrit Tjeerd (Thierry)

AU - Karabatı, Selçuk

AU - Arvanitis, Stelios

PY - 2018/9/1

Y1 - 2018/9/1

N2 - This study develops a portfolio optimization method based on the Stochastic Dominance (SD) decision criterion and the Empirical Likelihood (EL) estimation method. SD and EL share a distribution-free assumption framework which allows for dynamic and non-Gaussian multivariate return distributions. The SD/EL method can be implemented using a two-stage procedure which first elicits the implied probabilities using Convex Optimization and subsequently constructs the optimal portfolio using Linear Programming. The solution asymptotically dominates the benchmark and optimizes the goal function in probability, for a class of weakly dependent processes. A Monte Carlo simulation experiment illustrates the improvement in estimation precision using a set of conservative moment conditions about common factors in small samples. In an application to equity industry momentum strategies, SD/EL yields important out-of-sample performance improvements relative to heuristic diversification, Mean–Variance optimization, and a simple ‘plug-in’ approach.

AB - This study develops a portfolio optimization method based on the Stochastic Dominance (SD) decision criterion and the Empirical Likelihood (EL) estimation method. SD and EL share a distribution-free assumption framework which allows for dynamic and non-Gaussian multivariate return distributions. The SD/EL method can be implemented using a two-stage procedure which first elicits the implied probabilities using Convex Optimization and subsequently constructs the optimal portfolio using Linear Programming. The solution asymptotically dominates the benchmark and optimizes the goal function in probability, for a class of weakly dependent processes. A Monte Carlo simulation experiment illustrates the improvement in estimation precision using a set of conservative moment conditions about common factors in small samples. In an application to equity industry momentum strategies, SD/EL yields important out-of-sample performance improvements relative to heuristic diversification, Mean–Variance optimization, and a simple ‘plug-in’ approach.

KW - Empirical likelihood

KW - Momentum strategies

KW - Portfolio optimization

KW - Stochastic dominance

UR - http://www.scopus.com/inward/record.url?scp=85048887312&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048887312&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2018.01.011

DO - 10.1016/j.jeconom.2018.01.011

M3 - Article

VL - 206

SP - 167

EP - 186

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 1

ER -