Probabilities in a large sparse contingency table are estimated by maximizing the likelihood modified by a roughness penalty. It is shown that if certain smoothness criteria on the underlying probability vector are met, the estimator proposed is consistent in a one-dimensional table under a sparse asymptotic framework. Suggestions are made for techniques to apply the estimator in practice, and generalization to higher dimensional tables is considered.
Publié le : 1983-03-14
Classification:
Large sparse contingency tables,
smoothing of probability estimates,
maximum penalized likelihood,
sparse asymptotics,
62G05,
62E20
@article{1176346071,
author = {Simonoff, Jeffrey S.},
title = {A Penalty Function Approach to Smoothing Large Sparse Contingency Tables},
journal = {Ann. Statist.},
volume = {11},
number = {1},
year = {1983},
pages = { 208-218},
language = {en},
url = {http://dml.mathdoc.fr/item/1176346071}
}
Simonoff, Jeffrey S. A Penalty Function Approach to Smoothing Large Sparse Contingency Tables. Ann. Statist., Tome 11 (1983) no. 1, pp. 208-218. http://gdmltest.u-ga.fr/item/1176346071/