Simple correspondence analysis of ordinal cross-classifications using orthogonal polynomials

Abstract

A method is developed that caters for the application of correspondence analysis to two-way contingency tables with one and two ordered sets of categories. The method involves calculating orthogonal polynomials of the type described by EMERSON (1968), and partitioning the chi-square statistic using the method described in LANCASTER (1953). The method has all the features of simple correspondence analysis, although allows for additional information about the structure and association of the data to be made by isolating location, dispersion and higher order components of the rows and columns.