• 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
Full name
Jose Alberto Pereira da Silva
Knowledge Area
Date of Defense
São Paulo, 2003
Paula, Gilberto Alvarenga (President)
Elian, Silvia Nagib
Ortega, Edwin Moises Marcos
Title in Portuguese
Métodos de diagnóstico em modelos logísticos trinomiais
Keywords in Portuguese
Deleção de pontos
Influência local
Métodos diagnósticos
Modelo logístico trinomial
Pontos de alavanca
Abstract in Portuguese
Os modelos logísticos trinomiais podem ser interpretados como uma extensão natural do modelo logístico binomial para situações em que a resposta admite apenas três resultados. Introduzimos inicialmente os modelos logísticos trinomiais e discutiremos em seguida alguns aspectos inferenciais, tais como estimação e testes. Medidas de qualidade do ajuste são também apresentadas. Contudo, o principal foco deste trabalho é a apresentação de métodos de diagnóstico. Mostramos que as técnicas usuais de diagnóstico desenvolvidas para o modelo logístico binomial podem ser adaptadas para o caso trinomial. O desenvolvimento de métodos diretos para o modelo logístico trinomial é mais complexo do ponto de vista computacional, embora seja sempre possível. Discutimos alguns desses métodos, dentre os quais, o desenvolvimento de resíduos, de métodos para detectar pontos de alavanca, métodos de deleção de pontos e influência local. Comparamos os métodos adaptados com alguns métodos diretos através de exemplos.
Title in English
Methods of dignóstics in trinomials Logistic models
Keywords in English
Deletion methods
Local influence
Measures of high leverage points
Methods of dignóstics
Trinomials logistic models
Abstract in English
The trinomial logistic models can be interpreted as a natural extension of the traditional binomial logistic model to situations in which the response allows only three possible results. We firts introduce the trinomial logistic modles and then some inferential aspects, such as estimation and hypothesis testing are discussed. Good-of-fit measures are also given. However, the aim of this work is the presentation of some diagnostic procedures for trinomial logistic models. We show that methods developed for binomial logistic models can adapted straightforward for trinomial models. The developement of direct methods, even though possible, in general requires more complex calculation. Some of these direct methods, suchs as evaluation of residuals, measures of high leverage points, deletion methods and local influence are apresented. Coparisons between adapted and direct methods are made via examples with real data.
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
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2023. All rights reserved.