Minimum power-divergence estimator in three-way contingency tables
No Thumbnail Available
Full text at PDC
Publication date
2003
Authors
Pardo Llorente, MarĂa del Carmen
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Tailor and Francis
Citation
Abstract
Cressie et al. (2000; 2003) introduced and studied a new family of statistics, based on the phi-divergence measure, for solving the problem of testing a nested sequence of loglinear models. In that family of test statistics the parameters are estimated using the minimum phi-divergence estimator which is a generalization of the maximum likelihood estimator. In this paper we study the minimum power-divergence estimator (the most important family of minimum phi-divergence estimator) for a nested sequence of loglinear models in three-way contingency tables under assumptions of multinomial sampling. A simulation study illustrates that the minimum chi-squared estimator is simultaneously the most robust and efficient estimator among the family of the minimum power-divergence estimator.