Summary
Contents
This volume provides readers with a simple, non-technical introduction to correspondence analysis (CA), a technique for summarily describing the relationships among categorical variables in large tables. It begins with the history and logic of CA. The author shows readers the steps to the analysis: category profiles and masses are computed, the distances between these points calculated and the best-fitting space of n-dimensions located. There are glossaries on appropriate programs from SAS and SPSS for doing CA and the book concludes with a comparison of CA and log-linear models.
Analysis of Large Tables
Analysis of Large Tables
3.1. Tables with Two Variables
Let us now consider an analysis of a large two-way contingency table. The data are taken from the 1985 health survey in Norway (Statistics Norway, 1987). The main purpose of this survey was to obtain comprehensive knowledge of health problems in the Norwegian population. A total of 10,576 persons were interviewed, with a response rate of 78%. The data are shown in Table 3.1, and presented in a two-way contingency table with two polytomous variables: age (6 groups) and disease at time of interview (12 groups).
Table 3.2 ...