Geometrical and Combinatorial Nature of Pearson Residuals
Shusaku Tsumoto, Shoji Hirano · 2010
This paper focuses on residual analysis of statistical independence of multiple variables from the viewpoint of linear algebra. 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.