Using correspondence analysis to detect or verify similar questions in a survey

Kevin Donegan, Eric J. Beh, Peter Murray, Robert G. Clark, J. C. Rayner

    Research output: Chapter in Book / Conference PaperConference Paper

    Abstract

    ![CDATA[Correspondence analysis (CA) is a popular graphical procedure that is used to identify the association between two or more categorical variables. Survey questionnaires, by design or otherwise, often use several questions to assess a single characteristic. It is of interest to determine which questions appear to be measuring the same characteristic or to verify that certain questions are generating consistent answers. CA will be used to provide a graphical interpretation of the profile of responses to similar/different questions in a survey relating to the construction industry.]]
    Original languageEnglish
    Title of host publicationProceedings of the 2004 Workshop on Research Methods: Statistics and Finance
    PublisherUniversity of Wollongong
    Number of pages10
    ISBN (Print)1741281075
    Publication statusPublished - 2004
    EventWorkshop on Research Methods: Statistics and Finance -
    Duration: 1 Jan 2004 → …

    Conference

    ConferenceWorkshop on Research Methods: Statistics and Finance
    Period1/01/04 → …

    Keywords

    • correspondence analysis (statistics)
    • contingency tables
    • variables
    • construction industry
    • surveys
    • questions

    Fingerprint

    Dive into the research topics of 'Using correspondence analysis to detect or verify similar questions in a survey'. Together they form a unique fingerprint.

    Cite this