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.
The Essentials of Correspondence Analysis: A Simple Example
The Essentials of Correspondence Analysis: A Simple Example
Let us now analyze the data in Table 2.1 step by step. The data have been taken from Criminal Statistics 1984 (Statistics Norway, 1986) and show a cross-classification of crimes investigated by the police and different areas in Norway. Data were available for the entire country, but for illustrative purposes only three areas are shown. Likewise, only three types of all crimes investigated are shown: burglary, fraud, and vandalism. The advantages of the method are greatest, however, when it is used to analyze large tables.
The analysis is first carried out separately for ...