Bayesian portfolio selection using a multifactor model

Tomohiro Ando

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

This article develops a new portfolio selection method using Bayesian theory. The proposed method accounts for the uncertainties in estimation parameters and the model specification itself, both of which are ignored by the standard mean-variance method. The critical issue in constructing an appropriate predictive distribution for asset returns is evaluating the goodness of individual factors and models. This problem is investigated from a statistical point of view; we propose using the Bayesian predictive information criterion. Two Bayesian methods and the standard mean-variance method are compared through Monte Carlo simulations and in a real financial data set. The Bayesian methods perform very well compared to the standard mean-variance method.

Original languageEnglish
Pages (from-to)550-566
Number of pages17
JournalInternational Journal of Forecasting
Volume25
Issue number3
DOIs
Publication statusPublished - 2009 Jul

Fingerprint

Portfolio selection
Multifactor model
Bayesian methods
Mean-variance
Financial data
Individual factors
Information criterion
Predictive distribution
Asset returns
Monte Carlo simulation
Parameter estimation
Model specification
Individual model
Uncertainty

Keywords

  • Bayesian methods
  • Decision making
  • Finance
  • Model selection

ASJC Scopus subject areas

  • Business and International Management

Cite this

Bayesian portfolio selection using a multifactor model. / Ando, Tomohiro.

In: International Journal of Forecasting, Vol. 25, No. 3, 07.2009, p. 550-566.

Research output: Contribution to journalArticle

Ando, Tomohiro. / Bayesian portfolio selection using a multifactor model. In: International Journal of Forecasting. 2009 ; Vol. 25, No. 3. pp. 550-566.
@article{d308c1a5518d4126a8b5f5b0207cfcb6,
title = "Bayesian portfolio selection using a multifactor model",
abstract = "This article develops a new portfolio selection method using Bayesian theory. The proposed method accounts for the uncertainties in estimation parameters and the model specification itself, both of which are ignored by the standard mean-variance method. The critical issue in constructing an appropriate predictive distribution for asset returns is evaluating the goodness of individual factors and models. This problem is investigated from a statistical point of view; we propose using the Bayesian predictive information criterion. Two Bayesian methods and the standard mean-variance method are compared through Monte Carlo simulations and in a real financial data set. The Bayesian methods perform very well compared to the standard mean-variance method.",
keywords = "Bayesian methods, Decision making, Finance, Model selection",
author = "Tomohiro Ando",
year = "2009",
month = "7",
doi = "10.1016/j.ijforecast.2009.01.005",
language = "English",
volume = "25",
pages = "550--566",
journal = "International Journal of Forecasting",
issn = "0169-2070",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Bayesian portfolio selection using a multifactor model

AU - Ando, Tomohiro

PY - 2009/7

Y1 - 2009/7

N2 - This article develops a new portfolio selection method using Bayesian theory. The proposed method accounts for the uncertainties in estimation parameters and the model specification itself, both of which are ignored by the standard mean-variance method. The critical issue in constructing an appropriate predictive distribution for asset returns is evaluating the goodness of individual factors and models. This problem is investigated from a statistical point of view; we propose using the Bayesian predictive information criterion. Two Bayesian methods and the standard mean-variance method are compared through Monte Carlo simulations and in a real financial data set. The Bayesian methods perform very well compared to the standard mean-variance method.

AB - This article develops a new portfolio selection method using Bayesian theory. The proposed method accounts for the uncertainties in estimation parameters and the model specification itself, both of which are ignored by the standard mean-variance method. The critical issue in constructing an appropriate predictive distribution for asset returns is evaluating the goodness of individual factors and models. This problem is investigated from a statistical point of view; we propose using the Bayesian predictive information criterion. Two Bayesian methods and the standard mean-variance method are compared through Monte Carlo simulations and in a real financial data set. The Bayesian methods perform very well compared to the standard mean-variance method.

KW - Bayesian methods

KW - Decision making

KW - Finance

KW - Model selection

UR - http://www.scopus.com/inward/record.url?scp=67649742284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649742284&partnerID=8YFLogxK

U2 - 10.1016/j.ijforecast.2009.01.005

DO - 10.1016/j.ijforecast.2009.01.005

M3 - Article

AN - SCOPUS:67649742284

VL - 25

SP - 550

EP - 566

JO - International Journal of Forecasting

JF - International Journal of Forecasting

SN - 0169-2070

IS - 3

ER -