Abstract
For a multidimensional contingency table, we obtain several necessary and sufficient conditions for collapsibility and strict collapsibility, using the technique of Möbius inversion formula. As a consequence, the results of Whittemore (Journal of the Royal Statistical Society B, 40, 328–340, 1978) are stated in a form which is easy to understand and the proofs are much simpler and straightforward. Several new results on collapsibility and strict collapsibility with respect to more than one interaction parameter, are established, and their relationships to conditional independence are also pointed out. As applications of our results, several typical examples on collapsibility, strict collapsibility and conditional independence are discussed. It is also shown that Bishop et al. (Discrete Multivariate Analysis: Theory and Practice, MIT Press, Cambridge, 1975) conditions are necessary and sufficient for strict collapsibility with respect to a set of interaction factors.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Andersen E.B. (1990). The statistical analysis of categorical data. Berlin, Heidelberg New York: Springer
Birch M.W. (1963). Maximum likelihood in three-way contingency tables. Journal of the Royal Statistical Society B, 25: 220–233
Bishop Y.M.M., Fienberg S.E., Holland P.W. (1975). Discrete multivariate analysis: theory and practice. Cambridge: MIT Press
Charalambides A.C. (2002). Enumerative combinatorics. Florida: Chapman and Hall
Cox D.R., Wermuth N. (2003). A general condition for avoiding effect reversal after marginalization. Journal of the Royal Statistical Society B, 65: 937–941
Ducharme G.R. Lepage Y. (1986). Testing collapsibility in multidimensional tables. Journal of the Royal Statistical Society B, 48: 197–205
Guo J.H., Geng Z. (1995). Collapsibility of logistic regression coefficient. Journal of the Royal Statistical Society B, 57: 263–267
Hammersley J.M., Clifford P.E. (1971). Markov fields on finite graphs and lattices. Unpublished manuscript.
Lauritzen S.L. (1996). Graphical models. New York: Oxford University Press
Lindley D.V., Novick M.R. (1981). The role of exchangeability in inference. Annals of Statistics, 9: 45–58
Shapiro S.H. (1982). Collapsing contingency tables: a geometrical approach. American Statistician, 36: 43–46
Simonoff E.H. (2003). Analyzing categorical data. New York: Springer Berlin Heidelberg
Simpson E.H. (1951). The interpretation of interaction in contingency tables. Journal of the Royal Statistical Society B, 13: 238–241
Teugels J.L., Horebeek J.V. (1998). Generalized linear models for discrete data. Statistics & Probability Letters, 38, 41–47
Wermuth N. (1987). Parametric collapsibility and the lack of moderating effects in contingency tables with a dichotomous response variable. Journal of the Royal Statistical Society B, 49, 353–364
Whittaker J. (1990). Graphical models in applied multivariate statistics. Chichester: Wiley
Whittemore A.S. (1978). Collapsibility of multidimensional contingency tables. Journal of the Royal Statistical Society B, 40: 328–340
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Vellaisamy, P., Vijay, V. Some collapsibility results for n-dimensional contingency tables. AISM 59, 557–576 (2007). https://doi.org/10.1007/s10463-006-0058-4
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10463-006-0058-4
Keywords
- Collapsibility
- Conditional independence
- Contingency table
- Log-linear model
- Möbius inversion
- Simpson’s paradox
- Strict collapsibility