A Model Comparison Method for Hierarchical Loglinear Models

  • Hyun Jip Choi (Lecturer, Department of Applied Statistics, Kyonggi University, Paldal Gu, Suwon, 440-760, Korea) ;
  • Chong Sun Hong (Associate Professor, Department of Statistics, Sung Kyun Kwan University, Seoul, 110-745, Korea)
  • Published : 1996.12.01

Abstract

A hierarchical loglinear model comparison method is developed which is based on the well kmown partitioned likelihood ratio statistiss. For any paels, we can regard the difference of the geedness of fit statistics as the variation explained by a full model, and develop a partial test to compare a full model with a reduced model in that hierarchy. Note that this has similar arguments as that of the regression analysis.

Keywords

References

  1. Journal of American Statistical Association v.66 An analysis of variance for categorical data Light, R. J.;Margolin, B. H.
  2. Chemical Engineering Progress v.59 The use of chi-square for preference testing in multidimensional problems Ries, P. N.;Smith, H.
  3. Categorical Data Analysis Agresti, A.
  4. The Korean Communications in Statistics v.2 no.2 Graphical descriptions for hierarchical loglinear Models Choi, H. J.;Hong, C. S.
  5. Variailit e mutabilit, contributo allo studio edlle distribuzioni ; relazione statische Gini, C.
  6. Discrete Multivariate Analysis Bishop, Y. M. M.;Fienberg, S. E.;Holland, P. W.
  7. The Analysis of Cross-Classified Categorical Data Fienberg, S. E.
  8. The Analysis of Frequency Data Harberman, S. J.
  9. The Statistical Analysis of Categorical Data Andersen, E. B.
  10. Log-Linerar Model Christensen, R.