• 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.11.1984.tde-20220208-003740
Document
Author
Full name
Maria Eunice Oliveira de Castilho Rodrigues
Institute/School/College
Knowledge Area
Date of Defense
Published
Piracicaba, 1984
Supervisor
Title in Portuguese
Delineamento em ângulos
Keywords in Portuguese
DELINEAMENTO EXPERIMENTAL
MODELOS MATEMÁTICOS
Abstract in Portuguese
Foi apresentado um novo tipo de delineamento, denominado Delineamento em Ângulos; que tem por finalidade a ajustamento aos dados, de um polinômio do segundo grau, com duas variáveis. Nesse delineamento, foram considerados oito novos pontos, em relação ao delineamento composto central, escolhidos de modo a ortogonalizar o referido delineamento. O delineamento é formado por 16 + P pontos, onde P refere-se ao número de pontos centrais (0, 0), enquanto que 12 pontos dos demais referem-se a três fatoriais 2 x 2 nos quais os níveis estão codificados em -1 e +1, ± δ cos 30° e ± δ sen 30°, ± δ cos 60° e ± δ sen 60° e os quatro restantes estão codificados em (δ, 0), (-δ, 0), (0, δ) e (0, -δ). Foram obtidas as fórmulas que permitem a ortogonalização do delineamento e as que determinam as estimativas dos coeficientes do polinômio do segundo grau com suas respectivas estimativas das variâncias, quando o delineamento é ortogonal, bem como suas respectivas somas de quadrados. O Delineamento em Ângulos mostrou-se mais preciso que o Fatorial 32 e menos preciso do que os Fatoriais 52 e 72 na estimação dos coeficientes polinomiais. Levando em conta a mesma área total a ser gasta, o Delineamento em Ângulos é mais preciso quando se usa um ponto central e neste caso ele é mais preciso do que os fatoriais 52 e 72 na estimação dos coeficientes βi e β12 e menos preciso que o fatorial 32, 52 e 72 na estimação do coeficientes βii.
Title in English
Angle design
Abstract in English
A new design was developed specifically for fitting to data a second-degree polynomial equation with two variable, denominated ANGLE DESIGN. Criteria in constructing the design were: to make it orthogonal when two factors are involved, and nine levels of each of the factors. There were 16 treatment combinations and p central points. Of the 16 treatment combinations, four from each of three 22 factorial designs where the coded levels of the x-variable were -1 and +1, ± δ sin 30° and ± δ cosin 30°, ± δ sin 60° and ± δ cosin 60°, plus additional treatment combinations (δ, 0), (-δ, 0), (0, δ) and (0, -δ). Formulas to make the design orthogonal, to estimate the polynomial equation coefficients, to estimate the variances of the polynomial regression coefficients, and to estimate the sums of square of the polynomial equation coefficients, were determined. The Angle Design was more precise than the 32 factorial design and less precise than the 52 and 72 factorial designs when we consider the estimation of the polynomial equation coefficients. It was verified that the variances of the polynomial equation coefficients have a minimum when P = 1, in the Angle Design, when it was used the same area. When it was compared the precision of this design with one central point with the factorial designs, it was verified that it is more precise than the 52, and 72 factorial designs when it was considered the β̂i and β̂12 coefficients. On the other hand, it was less precise than the 32, 52, and 72 factorial designs, in the case of the β̂ii coefficient.
 
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.
Publishing Date
2022-02-08
 
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.