A Study on Cell Influences to Chi-square Statistic in Contingency Tables

  • Kim, Hong-Gie (Associate Professor, Department of Statistics, Chungnam National University)
  • Published : 1998.04.01

Abstract

Once a contingency table is constructed, the first interest will be the hypotheses of either homogeneity or independence depending on the sampling scheme. The most widely used test statistic in practice is the classical Pearson's $\chi^2$ statistic. When the null hypothesis is rejected, another natural interest becomes which cell contributed to the rejection of the null hypothesis more than others. For this purpose, so called cell $\chi^2$ components are investigated. In this paper, the influence function of a cell to the $\chi^2$ statistic is derived, which can be used for the same purpose. This function measures the effect of each cell to the $\chi$$^2$ statistic. A numerical example is given to demonstrate the role of the new function.

Keywords

References

  1. Biometrika v.72 Influence in principal components analysis Critchley, F.
  2. Biometrika v.36 A note on the subdivision of χ² into components Irwin, J.O.
  3. Journal of the Korean Communications in Statistics v.3 no.2 Influence Functions on χ² statistic in Contingency Tables Kim, H.;Lee, H.S.
  4. Applied Statistics v.29 An exploratory technique for investigating large quantities of categorical data Kass, G.
  5. Journal of American Statistical Association v.69 The influence curve and its role in robust estimation Hampel, F.
  6. Biometrics v.10 Short-cut formulars for the exact partitioning of χ² in contingency tables Kimball, A.W.
  7. Technometris v.22 Characterizations of an empirical influence function for detecting influential cases in regression Cook, R.D.;Weisberg, S.
  8. Theory and Applications of Correspondence Analysis Greenacre, M.J.
  9. The Korean Journal of Applied Statistics v.7 Influence functions in multiple correspondence analysis Kim, H.
  10. Applied Statistics v.27 The influence function as an aid in outlier detection in discriminant analysis Campbell, N.A.
  11. Biometrics v.16 A note on the additive partitioning of chi-square in contingency tables Kastenbaum, M.A.
  12. Journal of Statistical Computation and Simulation v.40 Measures of influence in correspondence analysis Kim, H.
  13. Psychometrika v.36 Measurement as structural theory Guttman, L.
  14. Residuals and Influence in Regression Cook, R.D.;Weisberg, S.