Coding categorical data for simple correspondence analysis

Eric J. Beh, V. Pemajayantha, Robert Mellor, M. Shelton Peiris, Jay R. Rajasekera

    Research output: Chapter in Book / Conference PaperConference Paper

    Abstract

    ![CDATA[Simple correspondence analysis is a very popular exploratory tool used to graphically identify the association between two categorical variables. It is generally performed by applying singular value decomposition on the standardised cell values of the contingency table. Analysing the counts summarised in the contingency table is the most common way to perform correspondence analysis, although categorical data can be coded in different ways. By applying simple correspondence analysis to this coded data we can also obtain a graphical description of the relationship between the variables. The benefit of such coding procedures is that they provide a natural extension for the analysis of multivariate categorical data. This paper will explore several ways that simple correspondence analysis can be performed by coding categorical data. Such a review supplements an extensive discussion recently made by Beh (2004) on a variety of issues concerned with the correspondence analysis of two categorical variables.]]
    Original languageEnglish
    Title of host publicationCurrent Research in Modelling, Data Mining & Quantitative Techniques
    PublisherUniversity of Western Sydney
    Number of pages15
    ISBN (Electronic)0975159909
    ISBN (Print)9780975159903
    Publication statusPublished - 2003
    EventWorkshop on Advanced Research Methods -
    Duration: 1 Jan 2003 → …

    Conference

    ConferenceWorkshop on Advanced Research Methods
    Period1/01/03 → …

    Keywords

    • correspondence analysis (statistics)
    • matrices
    • contingency tables
    • variables (mathematics)
    • multivariate analysis
    • data processing

    Fingerprint

    Dive into the research topics of 'Coding categorical data for simple correspondence analysis'. Together they form a unique fingerprint.

    Cite this