Statistical estimation of optimal portfolios for non-Gaussian dependent returns of assets

Hiroshi Shiraishi, Masanobu Taniguchi

    Research output: Contribution to journalArticle

    2 Citations (Scopus)

    Abstract

    This paper discusses the asymptotic efficiency of estimators for optimal portfolios when returns are vector-valued non-Gaussian stationary processes. We give the asymptotic distribution of portfolio estimators ĝ for non-Gaussian dependent return processes. Next we address the problem of asymptotic efficiency for the class of estimators ĝ. First, it is shown that there are some cases when the asymptotic variance of ĝ under non-Gaussianity can be smaller than that under Gaussianity. The result shows that non-Gaussianity of the returns does not always affect the efficiency badly. Second, we give a necessary and sufficient condition for ĝ to be asymptotically efficient when the return process is Gaussian, which shows that ĝ is not asymptotically efficient generally. From this point of view we propose to use maximum likelihood type estimators for g, which are asymptotically efficient. Furthermore, we investigate the problem of predicting the one-step-ahead optimal portfolio return by the estimated portfolio based on ĝ and examine the mean squares prediction error.

    Original languageEnglish
    Pages (from-to)193-215
    Number of pages23
    JournalJournal of Forecasting
    Volume27
    Issue number3
    DOIs
    Publication statusPublished - 2008 Apr

    Fingerprint

    Statistical Estimation
    Optimal Portfolio
    assets
    Estimator
    efficiency
    Asymptotic Efficiency
    Dependent
    prediction
    Maximum likelihood
    Asymptotic Variance
    Prediction Error
    Stationary Process
    Mean square error
    Asymptotic distribution
    Maximum Likelihood
    Necessary Conditions
    distribution
    Statistical estimation
    Assets
    Optimal portfolio

    Keywords

    • Asymptotic efficiency
    • Non-Gaussian linear process
    • Optimal portfolio
    • Prediction error
    • Return process
    • Spectral density

    ASJC Scopus subject areas

    • Management of Technology and Innovation
    • Strategy and Management
    • Development
    • Safety, Risk, Reliability and Quality

    Cite this

    Statistical estimation of optimal portfolios for non-Gaussian dependent returns of assets. / Shiraishi, Hiroshi; Taniguchi, Masanobu.

    In: Journal of Forecasting, Vol. 27, No. 3, 04.2008, p. 193-215.

    Research output: Contribution to journalArticle

    @article{269eb2e9dac04996a9604091c3fabdc0,
    title = "Statistical estimation of optimal portfolios for non-Gaussian dependent returns of assets",
    abstract = "This paper discusses the asymptotic efficiency of estimators for optimal portfolios when returns are vector-valued non-Gaussian stationary processes. We give the asymptotic distribution of portfolio estimators ĝ for non-Gaussian dependent return processes. Next we address the problem of asymptotic efficiency for the class of estimators ĝ. First, it is shown that there are some cases when the asymptotic variance of ĝ under non-Gaussianity can be smaller than that under Gaussianity. The result shows that non-Gaussianity of the returns does not always affect the efficiency badly. Second, we give a necessary and sufficient condition for ĝ to be asymptotically efficient when the return process is Gaussian, which shows that ĝ is not asymptotically efficient generally. From this point of view we propose to use maximum likelihood type estimators for g, which are asymptotically efficient. Furthermore, we investigate the problem of predicting the one-step-ahead optimal portfolio return by the estimated portfolio based on ĝ and examine the mean squares prediction error.",
    keywords = "Asymptotic efficiency, Non-Gaussian linear process, Optimal portfolio, Prediction error, Return process, Spectral density",
    author = "Hiroshi Shiraishi and Masanobu Taniguchi",
    year = "2008",
    month = "4",
    doi = "10.1002/for.1053",
    language = "English",
    volume = "27",
    pages = "193--215",
    journal = "Journal of Forecasting",
    issn = "0277-6693",
    publisher = "John Wiley and Sons Ltd",
    number = "3",

    }

    TY - JOUR

    T1 - Statistical estimation of optimal portfolios for non-Gaussian dependent returns of assets

    AU - Shiraishi, Hiroshi

    AU - Taniguchi, Masanobu

    PY - 2008/4

    Y1 - 2008/4

    N2 - This paper discusses the asymptotic efficiency of estimators for optimal portfolios when returns are vector-valued non-Gaussian stationary processes. We give the asymptotic distribution of portfolio estimators ĝ for non-Gaussian dependent return processes. Next we address the problem of asymptotic efficiency for the class of estimators ĝ. First, it is shown that there are some cases when the asymptotic variance of ĝ under non-Gaussianity can be smaller than that under Gaussianity. The result shows that non-Gaussianity of the returns does not always affect the efficiency badly. Second, we give a necessary and sufficient condition for ĝ to be asymptotically efficient when the return process is Gaussian, which shows that ĝ is not asymptotically efficient generally. From this point of view we propose to use maximum likelihood type estimators for g, which are asymptotically efficient. Furthermore, we investigate the problem of predicting the one-step-ahead optimal portfolio return by the estimated portfolio based on ĝ and examine the mean squares prediction error.

    AB - This paper discusses the asymptotic efficiency of estimators for optimal portfolios when returns are vector-valued non-Gaussian stationary processes. We give the asymptotic distribution of portfolio estimators ĝ for non-Gaussian dependent return processes. Next we address the problem of asymptotic efficiency for the class of estimators ĝ. First, it is shown that there are some cases when the asymptotic variance of ĝ under non-Gaussianity can be smaller than that under Gaussianity. The result shows that non-Gaussianity of the returns does not always affect the efficiency badly. Second, we give a necessary and sufficient condition for ĝ to be asymptotically efficient when the return process is Gaussian, which shows that ĝ is not asymptotically efficient generally. From this point of view we propose to use maximum likelihood type estimators for g, which are asymptotically efficient. Furthermore, we investigate the problem of predicting the one-step-ahead optimal portfolio return by the estimated portfolio based on ĝ and examine the mean squares prediction error.

    KW - Asymptotic efficiency

    KW - Non-Gaussian linear process

    KW - Optimal portfolio

    KW - Prediction error

    KW - Return process

    KW - Spectral density

    UR - http://www.scopus.com/inward/record.url?scp=42549117208&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=42549117208&partnerID=8YFLogxK

    U2 - 10.1002/for.1053

    DO - 10.1002/for.1053

    M3 - Article

    AN - SCOPUS:42549117208

    VL - 27

    SP - 193

    EP - 215

    JO - Journal of Forecasting

    JF - Journal of Forecasting

    SN - 0277-6693

    IS - 3

    ER -