Multiple Correspondence Analysis (MCA) takes multiple categorical variables and seeks to identify associations between levels of those variables. MCA extends correspondence analysis from two variables to many. It can be thought of as analogous to principal component analysis for quantitative variables. Similar to other multivariate methods, it is a dimension reducing method; it represents the data as points in 2- or 3-dimensional space.
Multiple correspondence analysis is frequently used in the social sciences. It can be used in survey analysis to identify question agreement. It is also used in consumer research to identify potential markets for products.
For more information about multiple correspondence analysis, see LeRoux and Rouanet (2010).
Figure 7.1 Multiple Correspondence Analysis