Universidad Complutense de Madrid
E-Prints Complutense

Analysis of divergence in loglinear models when expected frequencies are subject to linear constraints

Impacto

Downloads

Downloads per month over past year

Pardo Llorente, Leandro and Menéndez Calleja, María Luisa (2006) Analysis of divergence in loglinear models when expected frequencies are subject to linear constraints. Metrika, 64 (1). pp. 63-76. ISSN 0026-1335

[img] PDF
Restringido a Repository staff only

168kB

Official URL: http://link.springer.com/article/10.1007%2Fs00184-006-0034-2


URLURL Type
http://link.springer.com/Publisher


Abstract

Consider the loglinear model for categorical data under the assumption of multinomial sampling. We are interested in testing between various hypotheses on the parameter space when we have some hypotheses relating to the parameters of the models that can be written in terms of constraints on the frequencies. The usual likelihood ratio test, with maximum likelihood estimator for the unspecified parameters, is generalized to tests based on phi-divergence statistics, using minimum phi-divergence estimator. These tests yield the classical likelihood ratio test as a special case. Asymptotic distributions for the new phi-divergence test statistics are derived under the null hypothesis.


Item Type:Article
Uncontrolled Keywords:asymptotic distribution; multinomial sampling; phi-divergence test statistics; loglinear models; maximum-likelihood methods; categorical-data; phi-divergences; estimator; distance.
Subjects:Sciences > Mathematics > Applied statistics
ID Code:17734
Deposited On:17 Jan 2013 09:21
Last Modified:12 Dec 2018 18:07

Origin of downloads

Repository Staff Only: item control page