×

The admissibility of the maximum likelihood estimator for decomposable log-linear interaction models for contingency tables. (English) Zbl 0894.62068

Summary: It is well known that for certain log-linear interaction models for contingency tables, i.e. those that are decomposable, the maximum likelihood estimator can be found explicitly. We will show that in such cases this estimator is admissible. The proof is based on a stepwise Bayes argument and is a generalization of a proof of the admissibility of the maximum likelihood estimator for the usual unconstrained multinomial model. It is then shown that this result is a special case of a result for discrete exponential families.

MSC:

62H17 Contingency tables
62C15 Admissibility in statistical decision theory
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] DOI: 10.1214/aos/1176344612 · Zbl 0401.62010 · doi:10.1214/aos/1176344612
[2] Andersen A.H., Scandinavian Journal of Statistics 1 pp 115– (1974)
[3] Barndroff-Nielsen O., Information and Exponential Families in Statistical Theory (1978)
[4] DOI: 10.1214/aos/1176345645 · Zbl 0476.62006 · doi:10.1214/aos/1176345645
[5] Brown L.D., IMS monographs (1986)
[6] DOI: 10.1214/aos/1176345006 · Zbl 0444.62064 · doi:10.1214/aos/1176345006
[7] DOI: 10.1214/aos/1176344611 · Zbl 0405.62011 · doi:10.1214/aos/1176344611
[8] DOI: 10.2307/2283589 · doi:10.2307/2283589
[9] DOI: 10.2307/2283933 · Zbl 0217.51504 · doi:10.2307/2283933
[10] Haberman S.J., IMS monographs (1974)
[11] DOI: 10.1214/aos/1176344735 · Zbl 0437.62008 · doi:10.1214/aos/1176344735
[12] DOI: 10.1214/aoms/1177693156 · Zbl 0246.62017 · doi:10.1214/aoms/1177693156
[13] Lehmann E.L., Theory of Point Estimation (1983) · Zbl 0522.62020
[14] Rockafellar R.T., Convex Analysis (1970) · Zbl 0193.18401
[15] Wald A., Proc. Second Berk, Syrnp. Math. Statist, and Prob pp 149– (1951)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.