Residual Analysis of Statistical Dependence in Multiway Contingency Tables
A Pearson residual is defined as the residual between actual values and expected ones of each cell in a contingency table. This paper shows that this residual is represented as linear sum of determinants of 2 ×2, which suggests that the geometrical nature of the residuals can be viewed from grasmmanian algebra.
Unable to display preview. Download preview PDF.
- 1.Everitt, B.: The Analysis of Contingency Tables, 2nd edn. Chapman & Hall/CRC, Boca Raton (1992)Google Scholar
- 3.Tsumoto, S., Hirano, S.: Meaning of pearson residuals - linear algebra view. In: Proceedings of IEEE GrC 2007. IEEE press, Los Alamitos (2007)Google Scholar
- 5.Tsumoto, S., Hirano, S.: Dependency and granularity indata. In: Meyers, R.A. (ed.) Encyclopedia of Complexity and Systems Science, pp. 1864–1872. Springer, Heidelberg (2009)Google Scholar