Local influence analysis in general spatial models

Xiaowen Dai, Libin Jin, Lei Shi, Cuiping Yang, Shuangzhe LIU

    Research output: Contribution to journalArticle

    Abstract

    We study the local influence in the general spatial model which includes the spatial autoregressive model and the spatial error model as two special cases. The stepwise local influence procedure is employed in our diagnostic analysis. We derive the local diagnostic measures in the general spatial model under three perturbation schemes, namely, the variance perturbation, dependent variable perturbation and explanatory variable perturbation schemes. A simulation example and two realdata examples are analysed in detail and they show that the stepwise local influence analysis is effective in identifying influential observations and is a powerful tool for uncovering masking effects.
    Original languageEnglish
    Pages (from-to)313-331
    Number of pages19
    JournalAStA Advances in Statistical Analysis
    Volume100
    Issue number3
    DOIs
    Publication statusPublished - 2016

    Fingerprint

    Influence Analysis
    Local Influence
    Spatial Model
    Diagnostics
    diagnostic
    Perturbation
    Influential Observations
    Error Model
    Masking
    Autoregressive Model
    simulation
    Spatial model
    Dependent
    Simulation

    Cite this

    Dai, Xiaowen ; Jin, Libin ; Shi, Lei ; Yang, Cuiping ; LIU, Shuangzhe. / Local influence analysis in general spatial models. In: AStA Advances in Statistical Analysis. 2016 ; Vol. 100, No. 3. pp. 313-331.
    @article{719d61f7acf040ff92cdec16810dbf33,
    title = "Local influence analysis in general spatial models",
    abstract = "We study the local influence in the general spatial model which includes the spatial autoregressive model and the spatial error model as two special cases. The stepwise local influence procedure is employed in our diagnostic analysis. We derive the local diagnostic measures in the general spatial model under three perturbation schemes, namely, the variance perturbation, dependent variable perturbation and explanatory variable perturbation schemes. A simulation example and two realdata examples are analysed in detail and they show that the stepwise local influence analysis is effective in identifying influential observations and is a powerful tool for uncovering masking effects.",
    keywords = "general spatial model, influential observation, perturbation scheme",
    author = "Xiaowen Dai and Libin Jin and Lei Shi and Cuiping Yang and Shuangzhe LIU",
    year = "2016",
    doi = "10.1007/s10182-015-0261-9",
    language = "English",
    volume = "100",
    pages = "313--331",
    journal = "AStA Advances in Statistical Analysis",
    issn = "0002-6018",
    publisher = "Springer Verlag",
    number = "3",

    }

    Local influence analysis in general spatial models. / Dai, Xiaowen; Jin, Libin; Shi, Lei; Yang, Cuiping; LIU, Shuangzhe.

    In: AStA Advances in Statistical Analysis, Vol. 100, No. 3, 2016, p. 313-331.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Local influence analysis in general spatial models

    AU - Dai, Xiaowen

    AU - Jin, Libin

    AU - Shi, Lei

    AU - Yang, Cuiping

    AU - LIU, Shuangzhe

    PY - 2016

    Y1 - 2016

    N2 - We study the local influence in the general spatial model which includes the spatial autoregressive model and the spatial error model as two special cases. The stepwise local influence procedure is employed in our diagnostic analysis. We derive the local diagnostic measures in the general spatial model under three perturbation schemes, namely, the variance perturbation, dependent variable perturbation and explanatory variable perturbation schemes. A simulation example and two realdata examples are analysed in detail and they show that the stepwise local influence analysis is effective in identifying influential observations and is a powerful tool for uncovering masking effects.

    AB - We study the local influence in the general spatial model which includes the spatial autoregressive model and the spatial error model as two special cases. The stepwise local influence procedure is employed in our diagnostic analysis. We derive the local diagnostic measures in the general spatial model under three perturbation schemes, namely, the variance perturbation, dependent variable perturbation and explanatory variable perturbation schemes. A simulation example and two realdata examples are analysed in detail and they show that the stepwise local influence analysis is effective in identifying influential observations and is a powerful tool for uncovering masking effects.

    KW - general spatial model

    KW - influential observation

    KW - perturbation scheme

    U2 - 10.1007/s10182-015-0261-9

    DO - 10.1007/s10182-015-0261-9

    M3 - Article

    VL - 100

    SP - 313

    EP - 331

    JO - AStA Advances in Statistical Analysis

    JF - AStA Advances in Statistical Analysis

    SN - 0002-6018

    IS - 3

    ER -