AcknowledgmentsWe would like to thank Ulrich Kockelkorn for proof reading and thorough advice in correspondence analysis, Mark Lindley and Hans-Peter Reutter for instruction about temperament, and Thomas Noll for inspiring discussions.
6 Appendix
6.1 Technical Details of Correspondence AnalysisIn this appendix we provide some more technical details relating singular value decomposition and correspondence analysis (Greenacre, 1984; Kockelkorn, 2000). The following theorem is crucial for analyzing the co-occurrence matrix in correspondence analysis: Theorem 1 (Generalized Singular Value Decomposition) Let be a positive definite symmetric matrix and a positive definite symmetric matrix. For any real-valued matrix of rank there exist an matrix a matrix with , and a diagonal matrix so that: Cf. Greenacre (1984) for a proof. For , Theorem 1 yields the ordinary singular value decomposition. If furthermore is symmetric, we get the familiar eigendecomposition. The columns of can be viewed as the column factors with singular values . Vice versa the rows of are the row factors with the same singular values . The magnitude of in each of the dimensions in the co-ordinate system spanned by the factors is then given by . For the matrix of relative frequencies and positive definite diagonal matrices and with the inverted relative frequencies of row and column features, respectively, on their diagonal, Theorem 1 yields: |