Multiple Correspondence Analysis and its applications


Correspondence analysis (CA) is a statistical visualization method for picturing the association between the levels of categorical variables. Specifically, simple and multiple correspondence analysis (MCA) is used to analyze two-way and multiway data respectively. Biplots play an important role in visualization of association. This paper overviews the popular approaches of MCA and discusses the role of biplots in CA. We discuss theoretical issues involved in different methods of MCA and demonstrate each of these methods through examples. The main aim of the present paper is to highlight the importance of MCA based on separate SVDs. We study the association pattern in mother-child behavior over time, using MCA based on separate SVDs.

Keywords: Simple Correspondence analysis, Multiple Correspondence Analysis, Biplot, Multi-way contingency table

Full Text: pdf

Creative Commons License
This work is licensed under a Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0 Italia License.