• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.11.1976.tde-20240301-152708
Document
Author
Full name
João José de Oliveira Filho
Institute/School/College
Date of Defense
Published
Piracicaba, 1976
Supervisor
Title in Portuguese
Polinômios ortogonais e ortonormais em análise de regressão polinomial com níveis arbitrários
Keywords in Portuguese
ANÁLISE DE REGRESSÃO POLINOMIAL
POLINÔMIOS ORTOGONAIS
POLINÔMIOS ORTONORMAIS
Abstract in Portuguese
Dois métodos de obtenção de conjuntos de polinômios ortonormais, em relação a um conjunto de pontos com intervalos arbitrários, são discutidos, abordando-se aspectos de ordem teórica e suas aplicações em análises de regressão polinomial. Esses métodos o de Gram-Schmidt e o de Christoffel-Darboux, determinam os conjuntos de polinômios ortonormais respectivamente pelas fórmulas de recorrência (Descrito na Dissertação). Para suas aplicações em análise de regressão elaboraram-se quatro experimentos fictícios do tipo inteiramente casualizados, com cinco repetições. Foram realizadas nove análises de variância, envolvendo equações de regressão de 2ª, 3ª e 4ª graus, concluindo-se que: a - em geral não há diferença que justifique o uso de um ou de outro método na determinação dos conjuntos de polinômios ortonormais; b - para efeito de análise de regressão polinomial a normalização dos polinômios é perfeitamente dispensável.
Abstract in English
Two methods are described for the construction of a set of polynomials which are orthonormal over a set of points with arbitrary spacing, approaching theoretic aspects and their applications in polynomial regression analysis. Gram-Schmidt and Christoffel-Oarboux method's were used for the determination of the orthonormal polynomials sets by recurrence relations respectively (See Dissertation). The applications of the regression analysis were made by the utilization of four fictitious experiments in the completely randomized design with five replications. Nine analyses of variance were carried out involving regression equations of 2nd , 3rd and 4th degrees and the following conclusions were drawn: a - in general there is no difference that justify the utilization of either method in the determination of the orthonormal polynomials sets. b - the polynomial's normalization is perfectely dispensable for effect of polynomial regression analysis.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
725588.pdf (6.64 Mbytes)
Publishing Date
2024-03-14
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.