• 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.11.1983.tde-20220207-172415
Document
Author
Full name
Cesar Pereira
Institute/School/College
Knowledge Area
Date of Defense
Published
Piracicaba, 1983
Supervisor
Title in Portuguese
Método para contornar o problema de estimativas negativas em componentes de variância
Keywords in Portuguese
COMPONENTES DE VARIÂNCIA
ESTIMATIVAS NEGATIVAS
Abstract in Portuguese
Numa análise de variância, a presença de correlação negativa entre os elementos de uma mesma parcela (correlação intra-classe) pode ocasionar estimativas negativas de componentes de variância no modelo de classificação hierárquica. O modelo matemático considerado foi: vijk = µ + ai + bij + eijk ao fazermos uma análise de variância no modelo de classificação hierárquica, considerando este modelo aleatório, misto (dois casos) ou fixo, se determinarmos uma estimativa de componente de variância negativo e pelo teste F bilateral a hipótese de nulidade for rejeitada ao nível α de significância, eliminamos o parâmetro correspondente no modelo matemático. Então o modelo yijk = µ + ai + bij + eijk passa para yijk = µ + ai + eijk e reestruturamos a análise de variância, supondo (descrito na tese) compomos um novo quadro de análise de variância a partir das somas de quadrados e respectivas esperanças matemáticas, através do método dos momentos. A partir do novo quadro de análise de variância estimamos os novos componentes de variância e a correlação intra-classe.
Title in English
Method to solve the problem of negative estimatives in components of variance
Abstract in English
The main purpose of the present work is to determine the new estimatives of the components of variance when its negative estimatives occur in the standard or hierarchical classification considering the following pattern: random, mixed or fixed, and the estimatives occur in the standard or hierarchical classification. This mathematical pattern was considered: vijk = µ + ai + bij + eijk When we make an analysis of variance in the hierarchical classification considering the pattern shown above, if we determine a estimative of component of negative variance and by the bilateral F test, the null hypothesis is rejected at the α level of meaning we eliminated the corresponding parameter in the mathematical model. So the nodel yijk = µ + ai + bij + eijk becomes yijk = µ + ai + eijk and we re-structure the analysis of variance, supposing: (see theses) we compose a new board of analysis of variance from the addition of same numbers and respective mathematical expectations across method of moments. From the new board of the analysis of variance we estimate the new components of variance and the into-class correlation.
 
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.
PereiraCesar.pdf (3.08 Mbytes)
Publishing Date
2022-02-07
 
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.