1. Universidade Federal do Rio Grande do Norte
2. Centro de Ciências Exatas e da Terra
3. DEST - Departamento de Estatística
4. CCET - DEST - Artigos publicados em periódicos

Title:	Improved heteroskedasticity likelihood ratio tests in symmetric nonlinear regression models
Authors:	Araújo, Mariana C. Cysneiros, Audrey H. M. A. Montenegro, Lourdes C.
Keywords:	Bartlett correction;Bootstrap;Likelihood ratio test;Modified profile likelihood ratio test
Issue Date:	Jul-2017
Publisher:	Springer
Citation:	ARAÚJO, Mariana C.; CYSNEIROS, Audrey H. M. A. ; MONTENEGRO, Lourdes C. . Improved heteroskedasticity likelihood ratio tests in symmetric nonlinear regression models. Statistical Papers (Online), Germany, p. 1-22, 2017. Disponível em: https://link.springer.com/article/10.1007%2Fs00362-017-0933-5. Acesso em: 07 dez. 2017.
Portuguese Abstract:	In this paper we address the issue of testing inference of the dispersion parameter in heteroscedastic symmetric nonlinear regression models considering small samples.We deriveBartlett corrections to improve the likelihood ratio as well modified profile likelihood ratio tests. Our results extend some of those obtained in Cordeiro (J Stat Comput Simul 74:609–620, 2004) and Ferrari et al. (J Stat Plan Inference 124:423– 437, 2004), who consider a symmetric nonlinear regression model and normal linear regression model, respectively. We also present the bootstrap and bootstrap Bartlett corrected likelihood ratio tests. Monte Carlo simulations are carried out to compare the finite sample performances of the three corrected tests and their uncorrected versions. The numerical evidence shows that the corrected modified profile likelihood ratio test, the bootstrap and bootstrap Bartlett corrected likelihood ratio test perform better than the other ones. We also present an empirical application.
URI:	https://repositorio.ufrn.br/handle/123456789/50959
Appears in Collections:	CCET - DEST - Artigos publicados em periódicos

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.