Jörg Blasius
Correspondence Analysis and Related Methods

Jörg Blasius

Jörg Blasius is professor of sociology at the University of Bonn. His research interests are exploratory data analysis, methods of empirical social research, urban sociology and the sociology of lifestyles.

Workshop contents and objectives

Correspondence analysis (CA) is a multivariate method for exploring any kind of cross-tabular data by converting such tables into graphical displays, called "maps", and related numerical statistics. Starting with an introduction to the geometric background of the method, this course introduces scaling techniques such as simple correspondence analysis, multiple correspondence analysis, categorical principal component analysis, and principal component analysis. Further, the course gives an overview of new developments in the field of CA such as joint correspondence analysis, subset correspondence analysis, and the biplot methodology. In addition to a large variety of examples from the social sciences, it will be shown how the methods can be used to assess the quality and comparability of survey data. Among others, examples for the latter come from the World Value Surveys and the International Social Survey Programme.

The software used are SPSS (module CATEGORIES) and the ca package in R.

Bibliography

Basic Texts

• Blasius, J. and V. Thiessen (2012): Assessing the Quality of Survey Data. London: Sage (available from March 2012).
• Greenacre, M. (2007): Correspondence Analysis in Practice. Boca Raton, Fl.: Chapman & Hall.

Further Readings

• Blasius, J. and M. Greenacre, eds. (1998): Visualization of Categorical Data. San Diego: Academic Press.
• Blasius, J. and A. Mühlichen (2010): Identifying Audience Segments Applying the "Social Space" Approach. In: Poetics, 38, pp. 69-89.
• Greenacre, M. and J. Blasius, eds. (1994): Correspondence Analysis in the Social Sciences. Recent Developments and Applications. London: Academic Press.
• Greenacre, M. and J. Blasius, eds. (2006): Multiple Correspondence Analysis and Related Methods. Boca Raton, Fl.: Chapman & Hall.

Prerequisites

Participants taking this course should have good familiarity of descriptive statistics and at least some experience with multivariate data analysis. This includes experience with statistical software, especially SPSS. Since it is not possible to cover the full range of possibilities in SPSS, we also will use the ca package in R. Experience with R is helpful, but not required.