Title: Combinatorics in Pearson residuals

Authors: Shusaku Tsumoto; Shoji Hirano

Addresses: Department of Medical Informatics, Faculty of Medicine, Shimane University, 89-1 Enya-cho Izumo 693-8501, Japan ' Department of Medical Informatics, Faculty of Medicine, Shimane University, 89-1 Enya-cho Izumo 693-8501, Japan

Abstract: This paper focuses on residual analysis of statistical independence of multiple variables from the viewpoint of linear algebra and combinatorics. The results show that multidimensional residuals are represented as linear sum of determinants of 2 × 2 submatrices, which can be viewed as information granules measuring the degree of statistical dependence. Furthermore, all the elements of information granules have combinatorial characteristics of index sets.

Keywords: granular computing; information granules; contingency matrix theory; statistical independence; Pearson residuals; combinatorics; residual analysis; multiple variables; linear algebra.

DOI: 10.1504/IJKESDP.2013.052719

International Journal of Knowledge Engineering and Soft Data Paradigms, 2013 Vol.4 No.1, pp.72 - 84

Published online: 19 Jul 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article