Cluster analysis for stable processes

Tsutomu Watanabe, Hiroshi Shiraishi, Masanobu Taniguchi

    Research output: Contribution to journalArticle

    Abstract

    It is known that various financial time series, e.g., daily log returns on a share price, foreign exchange rates, excess bond returns, etc., exhibit heavy-tailed behavior. Recently, discriminant analysis has been applied to financial time series, such as, the problem of credit rating for companies. In this article, we investigate the problem of classifying an -stable linear process into one of two categories with indices 1 and 2, respectively. We propose some discriminant criteria. It is shown that our discriminant statistics are consistent. The misclassification probabilities are also evaluated under contiguous hypotheses. Some numerical studies for an (AR(1)) process are given.

    Original languageEnglish
    Pages (from-to)1630-1642
    Number of pages13
    JournalCommunications in Statistics - Theory and Methods
    Volume39
    Issue number8-9
    DOIs
    Publication statusPublished - 2010 Jan

    Fingerprint

    Financial Time Series
    Stable Process
    Cluster Analysis
    Discriminant
    Misclassification Probability
    Credit Rating
    Foreign Exchange Rates
    Linear Process
    Discriminant Analysis
    Excess
    Numerical Study
    Statistics

    Keywords

    • Discriminant analysis
    • Functional limit theorem
    • Integrated periodogram
    • Linear process
    • Stable process

    ASJC Scopus subject areas

    • Statistics and Probability

    Cite this

    Cluster analysis for stable processes. / Watanabe, Tsutomu; Shiraishi, Hiroshi; Taniguchi, Masanobu.

    In: Communications in Statistics - Theory and Methods, Vol. 39, No. 8-9, 01.2010, p. 1630-1642.

    Research output: Contribution to journalArticle

    Watanabe, Tsutomu ; Shiraishi, Hiroshi ; Taniguchi, Masanobu. / Cluster analysis for stable processes. In: Communications in Statistics - Theory and Methods. 2010 ; Vol. 39, No. 8-9. pp. 1630-1642.
    @article{831fff9c7361447fa6d9a7ee94dca54b,
    title = "Cluster analysis for stable processes",
    abstract = "It is known that various financial time series, e.g., daily log returns on a share price, foreign exchange rates, excess bond returns, etc., exhibit heavy-tailed behavior. Recently, discriminant analysis has been applied to financial time series, such as, the problem of credit rating for companies. In this article, we investigate the problem of classifying an -stable linear process into one of two categories with indices 1 and 2, respectively. We propose some discriminant criteria. It is shown that our discriminant statistics are consistent. The misclassification probabilities are also evaluated under contiguous hypotheses. Some numerical studies for an (AR(1)) process are given.",
    keywords = "Discriminant analysis, Functional limit theorem, Integrated periodogram, Linear process, Stable process",
    author = "Tsutomu Watanabe and Hiroshi Shiraishi and Masanobu Taniguchi",
    year = "2010",
    month = "1",
    doi = "10.1080/03610920802155460",
    language = "English",
    volume = "39",
    pages = "1630--1642",
    journal = "Communications in Statistics - Theory and Methods",
    issn = "0361-0926",
    publisher = "Taylor and Francis Ltd.",
    number = "8-9",

    }

    TY - JOUR

    T1 - Cluster analysis for stable processes

    AU - Watanabe, Tsutomu

    AU - Shiraishi, Hiroshi

    AU - Taniguchi, Masanobu

    PY - 2010/1

    Y1 - 2010/1

    N2 - It is known that various financial time series, e.g., daily log returns on a share price, foreign exchange rates, excess bond returns, etc., exhibit heavy-tailed behavior. Recently, discriminant analysis has been applied to financial time series, such as, the problem of credit rating for companies. In this article, we investigate the problem of classifying an -stable linear process into one of two categories with indices 1 and 2, respectively. We propose some discriminant criteria. It is shown that our discriminant statistics are consistent. The misclassification probabilities are also evaluated under contiguous hypotheses. Some numerical studies for an (AR(1)) process are given.

    AB - It is known that various financial time series, e.g., daily log returns on a share price, foreign exchange rates, excess bond returns, etc., exhibit heavy-tailed behavior. Recently, discriminant analysis has been applied to financial time series, such as, the problem of credit rating for companies. In this article, we investigate the problem of classifying an -stable linear process into one of two categories with indices 1 and 2, respectively. We propose some discriminant criteria. It is shown that our discriminant statistics are consistent. The misclassification probabilities are also evaluated under contiguous hypotheses. Some numerical studies for an (AR(1)) process are given.

    KW - Discriminant analysis

    KW - Functional limit theorem

    KW - Integrated periodogram

    KW - Linear process

    KW - Stable process

    UR - http://www.scopus.com/inward/record.url?scp=77951982042&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77951982042&partnerID=8YFLogxK

    U2 - 10.1080/03610920802155460

    DO - 10.1080/03610920802155460

    M3 - Article

    AN - SCOPUS:77951982042

    VL - 39

    SP - 1630

    EP - 1642

    JO - Communications in Statistics - Theory and Methods

    JF - Communications in Statistics - Theory and Methods

    SN - 0361-0926

    IS - 8-9

    ER -