Contributions to the statistical analysis of contingency tables: Notes on quasi-symmetry, quasi-independence, log-linear models, log-bilinear models, and correspondence analysis models
نویسنده
چکیده
— This paper begins by comparing Henri Caussinus’ concept of quasi-symmetry with a related but different concept that I shall call Karl Pearson’s quasi-symmetry; and we shall find that Caussinus’ concept is preferable to and more useful than Pearson’s concept. I shall then introduce a set of quasi-symmetric log-bilinear models that are more (∗) Reçu le 18 septembre 2001, accepté le 18 septembre 2002 (1) Departments of Statistics and Sociology, University of California at Berkeley, Berkeley, California 94720, U.S.A. Email: [email protected]
منابع مشابه
Bayesian Methods for Two-way Contingency Tables
In this paper, we consider Bayesian estimation and model determination for two-way contingency tables. The analysis is based on partitioning the parameter space of a saturated log-linear model into parameter subspaces identiied by considering the natural symmetries of the data. Prior distributions may then be chosen to respect invariance restrictions required by the available prior information....
متن کاملQuasi-Symmetric Graphical Log-Linear Models
We propose an extension of graphical log-linear models to allow for symmetry constraints on some interaction parameters that represent homologous factors. The conditional independence structure of such quasi-symmetric (QS) graphical models is described by an undirected graph with coloured edges, in which a particular colour corresponds to a set of equality constraints on a set of parameters. Un...
متن کاملQuasi-symmetry and Representation Theory – 541 –
— Quasi-symmetry is a model for square contingency tables with rows and columns indexed by the same set. In a log-linear model, quasi-symmetry is associated with a vector subspace QSn of certain realvalued functions on n × n. Permutation of factor levels induces a linear transformation QSn → QSn, making this into a representation of the symmetric group Sn. However, there are many group represen...
متن کاملAlternative statistical models and representations for large sparse multi-dimensional contingency tables
— A variety of strategies allow one to approach the analysis of large sparse contingency tables using models with a modest number of parameters. This paper gives an overview of some of these strategies, emphasizing the role of log-linear models and exchangeability: multidimensional generalizations of the model of quasi-symmetry due to Henri Caussinus, Bayesian versions of the Rasch model from i...
متن کاملDecomposable Log-linear Models Decomposable Log-linear Models
The present paper considers discrete probability models with exact computational properties. In relation to contingency tables this means closed form expressions of the maksimum likelihood estimate and its distribution. The model class includes what is known as decomposable graphical models, which can be characterized by a structured set of conditional independencies between some variables give...
متن کامل