Algoritmo utilizando quadraturas gaussianas para a obtenção das probabilidades do teste bilateral de Dunnett para dados balanceados
DOI:
https://doi.org/10.1590/S2179-84512013005000010Abstract
O teste de Dunnett é um teste de comparações múltiplas em que se confrontam as médias de $r$ novos tratamentos com a média de um tratamento testemunha controlando simultaneamente a taxa de erro tipo I por experimento num valor específico $\alpha$. A limitação para o seu uso é a dificuldade de obter as probabilidades da distribuição e os valores dos quantis da estatística do teste, pois as correlações possíveis entre os tratamentos têm larga amplitude. Neste trabalho é apresentado um algoritmo para obter probabilidades relacionadas ao teste de Dunnett bilateral para dados balanceados utilizando para resolver as integrais métodos numéricos de quadratura gaussiana. O algoritmo apresentou resultados precisos quando comparados com valores das tabelas divulgadas na literatura e em relação aos valores obtidos nos três programas analisados.References
W. P. Dunlap; M. S. Marx; G. J. Agamy, FORTRAN IV functions for calculating probabilities associated with Dunnett’s test, Behavior Research Methods & Instrumentation , 13(3), (1981) 363-366.
C. Dunnett, Algorithm AS 251: Multivariate normal probabilities integrals with product correlation structure, Appl. Statist., 38,(1989), 564-579.
C. W. Dunnett; New Tables for Multiple Comparisons with a Control Biometrika, 20(3), (Sep., 1964), p. 482-491, 1964.
A. Genz; F. Bretz, Numerical computation of the multivariate t-probabilities with applications to power calculation of multiple contrasts, Journal of Statistical Computation and Simulation , 63(4),(1999), 361-378.
Y. Hochberg; A. C. Tamhane, “Multiple Comparisons Procedures”,John Wiley & Sons, Canadá, 1987.
J. C. Hsu, “Multiple Comparisons - Theory and methods”, Chapman& Hall, USA, 1999.
A. I. Khuri, “Advanced Calculus with Applications in Statistics”,Second Edition, John Wiley & Sons, USA, 2003.
R Development Core Team. R: a languague and environment for statistical computing. Vienna: R Foundation for Statistical Computing, 2011. Disponível em http://www.R-project.org > Acesso em: 20 mar. 2011.
M. J. Schervish, Algorithm AS 195: Multivariate normal probabilities with error bound. Appl. Statist., 33, (1984), 81-94.
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Authors who publish in this journal agree to the following terms:
Authors retain copyright and grant the journal the right of first publication, with the work simultaneously licensed under the Creative Commons Attribution License that allows the sharing of the work with acknowledgment of authorship and initial publication in this journal.
Authors are authorized to assume additional contracts separately, for non-exclusive distribution of the version of the work published in this journal (eg, publish in an institutional repository or as a book chapter), with acknowledgment of authorship and initial publication in this journal.
Authors are allowed and encouraged to publish and distribute their work online (eg, in institutional repositories or on their personal page) at any point before or during the editorial process, as this can generate productive changes as well as increase impact and the citation of the published work (See The effect of open access).
This is an open access journal which means that all content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, without asking prior permission from the publisher or the
author. This is in accordance with the BOAI definition of open access
Intellectual Property
All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License under attribution BY.