Assessing influence on the goodness-of-link in generalized linear models

Andy H. Lee, Yuejun Zhao

    Research output: Contribution to journalComment/debate

    Abstract

    The evidence for a hypothesized link function in a generalized linear model may depend crucially on one or a few observations. Global and local influence diagnostics are proposed to assess influence on the goodness-of-link test. It is found that the local influence method can reveal influential observations on the link even when masking is present.
    Original languageEnglish
    Pages (from-to)351-358
    Number of pages8
    JournalStatistics and Probability Letters
    Volume31
    Issue number4
    DOIs
    Publication statusPublished - 1997

    Fingerprint

    Dive into the research topics of 'Assessing influence on the goodness-of-link in generalized linear models'. Together they form a unique fingerprint.

    Cite this