Local influence analysis for Poisson autoregression with an application to stock transaction data

Fukang Zhu, Shuangzhe LIU, Lei Shi

    Research output: Contribution to journalArticle

    4 Citations (Scopus)

    Abstract

    In statistical diagnostics and sensitivity analysis, the local influence method plays an important role and has certain advantages over other methods in several situations. In this paper, we use this method to study time series of count data when employing a Poisson autoregressive model. We consider case-weights, scale, data, and additive perturbation schemes to obtain their corresponding vectors and matrices of derivatives for the measures of slope and normal curvatures. Based on the curvature diagnostics, we take a stepwise local influence approach to deal with data with possible masking effects. Finally, our established results are illustrated to be effective by analyzing a stock transactions data set.
    Original languageEnglish
    Pages (from-to)4-25
    Number of pages22
    JournalStatistica Neerlandica
    Volume70
    Issue number1
    DOIs
    Publication statusPublished - 2016

    Fingerprint

    Influence Analysis
    Local Influence
    Autoregression
    Transactions
    Siméon Denis Poisson
    Diagnostics
    Normal Curvature
    Count Data
    Poisson Model
    Masking
    Autoregressive Model
    Sensitivity Analysis
    Slope
    Time series
    Curvature
    Perturbation
    Derivative
    Transaction data

    Cite this

    @article{3388ef0ea8d341f6867bf84ffa87ca80,
    title = "Local influence analysis for Poisson autoregression with an application to stock transaction data",
    abstract = "In statistical diagnostics and sensitivity analysis, the local influence method plays an important role and has certain advantages over other methods in several situations. In this paper, we use this method to study time series of count data when employing a Poisson autoregressive model. We consider case-weights, scale, data, and additive perturbation schemes to obtain their corresponding vectors and matrices of derivatives for the measures of slope and normal curvatures. Based on the curvature diagnostics, we take a stepwise local influence approach to deal with data with possible masking effects. Finally, our established results are illustrated to be effective by analyzing a stock transactions data set.",
    keywords = "influential observation, local influence",
    author = "Fukang Zhu and Shuangzhe LIU and Lei Shi",
    year = "2016",
    doi = "10.1111/stan.12071",
    language = "English",
    volume = "70",
    pages = "4--25",
    journal = "Statistica Neerlandica",
    issn = "0039-0402",
    publisher = "Wiley-Blackwell",
    number = "1",

    }

    Local influence analysis for Poisson autoregression with an application to stock transaction data. / Zhu, Fukang; LIU, Shuangzhe; Shi, Lei.

    In: Statistica Neerlandica, Vol. 70, No. 1, 2016, p. 4-25.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Local influence analysis for Poisson autoregression with an application to stock transaction data

    AU - Zhu, Fukang

    AU - LIU, Shuangzhe

    AU - Shi, Lei

    PY - 2016

    Y1 - 2016

    N2 - In statistical diagnostics and sensitivity analysis, the local influence method plays an important role and has certain advantages over other methods in several situations. In this paper, we use this method to study time series of count data when employing a Poisson autoregressive model. We consider case-weights, scale, data, and additive perturbation schemes to obtain their corresponding vectors and matrices of derivatives for the measures of slope and normal curvatures. Based on the curvature diagnostics, we take a stepwise local influence approach to deal with data with possible masking effects. Finally, our established results are illustrated to be effective by analyzing a stock transactions data set.

    AB - In statistical diagnostics and sensitivity analysis, the local influence method plays an important role and has certain advantages over other methods in several situations. In this paper, we use this method to study time series of count data when employing a Poisson autoregressive model. We consider case-weights, scale, data, and additive perturbation schemes to obtain their corresponding vectors and matrices of derivatives for the measures of slope and normal curvatures. Based on the curvature diagnostics, we take a stepwise local influence approach to deal with data with possible masking effects. Finally, our established results are illustrated to be effective by analyzing a stock transactions data set.

    KW - influential observation

    KW - local influence

    U2 - 10.1111/stan.12071

    DO - 10.1111/stan.12071

    M3 - Article

    VL - 70

    SP - 4

    EP - 25

    JO - Statistica Neerlandica

    JF - Statistica Neerlandica

    SN - 0039-0402

    IS - 1

    ER -