Analysis of variance for high-dimensional time series

Hideaki Nagahata, Masanobu Taniguchi

    Research output: Contribution to journalArticle

    Abstract

    Analysis of variance (ANOVA) is tailored for independent observations. Recently, there has been considerable demand for ANOVA of high-dimensional and dependent observations in many fields. For example, it is important to analyze differences among industry averages of financial data. However, ANOVA for these types of observations has been inadequately developed. In this paper, we thus present a study of ANOVA for high-dimensional and dependent observations. Specifically, we present the asymptotics of classical test statistics proposed for independent observations and provide a sufficient condition for them to be asymptotically normal. Numerical examples for simulated and radioactive data are presented as applications of these results.

    Original languageEnglish
    Pages (from-to)455-468
    Number of pages14
    JournalStatistical Inference for Stochastic Processes
    Volume21
    Issue number2
    DOIs
    Publication statusPublished - 2018 Jul 1

    Fingerprint

    Analysis of variance
    High-dimensional
    Time series
    Dependent Observations
    Financial Data
    Test Statistic
    Industry
    Numerical Examples
    Sufficient Conditions
    Observation

    Keywords

    • Analysis of variance
    • DCC-GARCH model
    • High-dimensional dependent disturbance
    • Non-Gaussian vector stationary process

    ASJC Scopus subject areas

    • Statistics and Probability

    Cite this

    Analysis of variance for high-dimensional time series. / Nagahata, Hideaki; Taniguchi, Masanobu.

    In: Statistical Inference for Stochastic Processes, Vol. 21, No. 2, 01.07.2018, p. 455-468.

    Research output: Contribution to journalArticle

    @article{183389f5925943bb923483dfba35a095,
    title = "Analysis of variance for high-dimensional time series",
    abstract = "Analysis of variance (ANOVA) is tailored for independent observations. Recently, there has been considerable demand for ANOVA of high-dimensional and dependent observations in many fields. For example, it is important to analyze differences among industry averages of financial data. However, ANOVA for these types of observations has been inadequately developed. In this paper, we thus present a study of ANOVA for high-dimensional and dependent observations. Specifically, we present the asymptotics of classical test statistics proposed for independent observations and provide a sufficient condition for them to be asymptotically normal. Numerical examples for simulated and radioactive data are presented as applications of these results.",
    keywords = "Analysis of variance, DCC-GARCH model, High-dimensional dependent disturbance, Non-Gaussian vector stationary process",
    author = "Hideaki Nagahata and Masanobu Taniguchi",
    year = "2018",
    month = "7",
    day = "1",
    doi = "10.1007/s11203-018-9187-7",
    language = "English",
    volume = "21",
    pages = "455--468",
    journal = "Statistical Inference for Stochastic Processes",
    issn = "1387-0874",
    publisher = "Springer Netherlands",
    number = "2",

    }

    TY - JOUR

    T1 - Analysis of variance for high-dimensional time series

    AU - Nagahata, Hideaki

    AU - Taniguchi, Masanobu

    PY - 2018/7/1

    Y1 - 2018/7/1

    N2 - Analysis of variance (ANOVA) is tailored for independent observations. Recently, there has been considerable demand for ANOVA of high-dimensional and dependent observations in many fields. For example, it is important to analyze differences among industry averages of financial data. However, ANOVA for these types of observations has been inadequately developed. In this paper, we thus present a study of ANOVA for high-dimensional and dependent observations. Specifically, we present the asymptotics of classical test statistics proposed for independent observations and provide a sufficient condition for them to be asymptotically normal. Numerical examples for simulated and radioactive data are presented as applications of these results.

    AB - Analysis of variance (ANOVA) is tailored for independent observations. Recently, there has been considerable demand for ANOVA of high-dimensional and dependent observations in many fields. For example, it is important to analyze differences among industry averages of financial data. However, ANOVA for these types of observations has been inadequately developed. In this paper, we thus present a study of ANOVA for high-dimensional and dependent observations. Specifically, we present the asymptotics of classical test statistics proposed for independent observations and provide a sufficient condition for them to be asymptotically normal. Numerical examples for simulated and radioactive data are presented as applications of these results.

    KW - Analysis of variance

    KW - DCC-GARCH model

    KW - High-dimensional dependent disturbance

    KW - Non-Gaussian vector stationary process

    UR - http://www.scopus.com/inward/record.url?scp=85049597566&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85049597566&partnerID=8YFLogxK

    U2 - 10.1007/s11203-018-9187-7

    DO - 10.1007/s11203-018-9187-7

    M3 - Article

    AN - SCOPUS:85049597566

    VL - 21

    SP - 455

    EP - 468

    JO - Statistical Inference for Stochastic Processes

    JF - Statistical Inference for Stochastic Processes

    SN - 1387-0874

    IS - 2

    ER -