Correspondence analysis used complementary to loglinear analysis (Q1821457)

The authors show that loglinear analysis and correspondence analysis are two methods for the decomposition of contingency tables that are often complementary. In this case, it is shown that correspondence analysis can be viewed as providing a decomposition of the difference between two matrices, each following a specific loglinear model. Using a generalization of correspondence analysis for multiple tables, the same property is shown. In this way, a contingency table with data on suicide behavior is analysed.