Statistical estimation of optimal portfolios for locally stationary returns of assets

Hiroshi Shiraishi, Masanobu Taniguchi

研究成果: Article

2 引用 (Scopus)

抄録

This paper discusses the asymptotic property of estimators for optimal portfolios when the returns are vector-valued locally stationary processes. First, we derive the asymptotic distribution of a nonparametric portfolio estimator based on the kernel method. Optimal bandwidth and kernel function are given by minimizing the mean squares error of it. Next, assuming parametric models for non-Gaussian locally stationary processes, we prove the LAN theorem, and propose a parametric portfolio estimator ĝ based on a quasi-maximum likelihood estimator. Then it is shown that ĝ is asymptotically efficient based on the LAN. Numerical studies are provided to investigate the accuracy of the portfolio estimators parametrically and nonparametrically. They illuminate some interesting features of them.

元の言語English
ページ(範囲)129-154
ページ数26
ジャーナルInternational Journal of Theoretical and Applied Finance
10
発行部数1
DOI
出版物ステータスPublished - 2007 2
外部発表Yes

Fingerprint

Assets
Statistical estimation
Optimal portfolio
Estimator
Stationary process
Local area networks
Kernel
Kernel methods
Asymptotic distribution
Quasi-maximum likelihood estimator
Asymptotic properties
Parametric model
Bandwidth

ASJC Scopus subject areas

  • Economics, Econometrics and Finance(all)

これを引用

@article{8182aeb5febf4819929496fc4cb27386,
title = "Statistical estimation of optimal portfolios for locally stationary returns of assets",
abstract = "This paper discusses the asymptotic property of estimators for optimal portfolios when the returns are vector-valued locally stationary processes. First, we derive the asymptotic distribution of a nonparametric portfolio estimator based on the kernel method. Optimal bandwidth and kernel function are given by minimizing the mean squares error of it. Next, assuming parametric models for non-Gaussian locally stationary processes, we prove the LAN theorem, and propose a parametric portfolio estimator ĝ based on a quasi-maximum likelihood estimator. Then it is shown that ĝ is asymptotically efficient based on the LAN. Numerical studies are provided to investigate the accuracy of the portfolio estimators parametrically and nonparametrically. They illuminate some interesting features of them.",
keywords = "Asymptotic efficiency, Kernel method, Locally asymptotic normality, Locally stationary process, Optimal portfolio",
author = "Hiroshi Shiraishi and Masanobu Taniguchi",
year = "2007",
month = "2",
doi = "10.1142/S0219024907004093",
language = "English",
volume = "10",
pages = "129--154",
journal = "International Journal of Theoretical and Applied Finance",
issn = "0219-0249",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "1",

}

TY - JOUR

T1 - Statistical estimation of optimal portfolios for locally stationary returns of assets

AU - Shiraishi, Hiroshi

AU - Taniguchi, Masanobu

PY - 2007/2

Y1 - 2007/2

N2 - This paper discusses the asymptotic property of estimators for optimal portfolios when the returns are vector-valued locally stationary processes. First, we derive the asymptotic distribution of a nonparametric portfolio estimator based on the kernel method. Optimal bandwidth and kernel function are given by minimizing the mean squares error of it. Next, assuming parametric models for non-Gaussian locally stationary processes, we prove the LAN theorem, and propose a parametric portfolio estimator ĝ based on a quasi-maximum likelihood estimator. Then it is shown that ĝ is asymptotically efficient based on the LAN. Numerical studies are provided to investigate the accuracy of the portfolio estimators parametrically and nonparametrically. They illuminate some interesting features of them.

AB - This paper discusses the asymptotic property of estimators for optimal portfolios when the returns are vector-valued locally stationary processes. First, we derive the asymptotic distribution of a nonparametric portfolio estimator based on the kernel method. Optimal bandwidth and kernel function are given by minimizing the mean squares error of it. Next, assuming parametric models for non-Gaussian locally stationary processes, we prove the LAN theorem, and propose a parametric portfolio estimator ĝ based on a quasi-maximum likelihood estimator. Then it is shown that ĝ is asymptotically efficient based on the LAN. Numerical studies are provided to investigate the accuracy of the portfolio estimators parametrically and nonparametrically. They illuminate some interesting features of them.

KW - Asymptotic efficiency

KW - Kernel method

KW - Locally asymptotic normality

KW - Locally stationary process

KW - Optimal portfolio

UR - http://www.scopus.com/inward/record.url?scp=33846438586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846438586&partnerID=8YFLogxK

U2 - 10.1142/S0219024907004093

DO - 10.1142/S0219024907004093

M3 - Article

AN - SCOPUS:33846438586

VL - 10

SP - 129

EP - 154

JO - International Journal of Theoretical and Applied Finance

JF - International Journal of Theoretical and Applied Finance

SN - 0219-0249

IS - 1

ER -