• 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
 
 
Doctoral Thesis
DOI
https://doi.org/10.11606/T.104.2023.tde-24082023-110019
Document
Author
Full name
Eriton Barros dos Santos
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2023
Supervisor
Committee
Milan, Luis Aparecido (President)
Saraiva, Erlandson Ferreira
Souza, Anderson Luiz Ara
Tsunemi, Miriam Harumi
Zuanetti, Daiane Aparecida
Title in Portuguese
Seleção de covariância para o modelo grafo gaussiano via reversible jump
Keywords in Portuguese
Correlação parcial
Grafo Gaussiano
Metropolis-Hastings
Modelo grafo
Modelo grafo Gaussiano
Reversible jump
Seleção de covariância
Seleção de modelo
Abstract in Portuguese
O objetivo do modelo grafo gaussiano consiste em encontrar a estrutura de covariância que representa a relação entre variáveis aleatórias, cuja distribuição conjunta é uma normal multivariada. Isso é uma ferramenta usada para modelar grafos gaussianos. A inferência de parâmetros desse tipo de modelagem geralmente é baseada na estimativa da máxima verossimilhança. No entanto, esse tipo de metodologia requer o ajuste de todos os modelos possíveis para verificar qual modelo melhor representa a relação entre as variáveis. No caso de qualquer modelo, dentre todos os possíveis, apresentar problema de estimativa, o resultado pode não representar a verdadeira relação entre as variáveis. Nós propomos alterações no procedimento baseado no algoritmo Reversible Jump de Dobra et al. (2011) para seleção e ajuste do modelo grafo gaussiano. Nós também criamos indicadores para avaliar resultados de simulações provenientes de um modelo grafo gaussiano. Os resultados obtidos no trabalho são favoráveis a nossa proposta apresentada, no qual observou um melhoramento no método de seleção de modelo diminuindo o erro ao buscar a estrutura de covariância.
Title in English
Covariance Selection for Graphical Gaussian Model via Reversible Jump
Keywords in English
Covariance selection model
Gaussian Graphs
Graphical Gaussian model
Graphical model
Metropolis-Hastings
Model selection
Partial correlation
Reversible jump
Abstract in English
The purpose of the Graphical Gaussian model is to find the covariance structure that represents the relationship between random variables, whose joint distribution is a multivariate normal. This is a tool used to modeling Gaussian graphs. The inference of parameters of this type of modeling is commonly based on maximum likelihood estimation. However, this type of methodology requires the adjustment of all possible models to verify which model best represents the relationship between the variables. In case any model, among all the possibilities, presents an estimation problem, the result may not represent the true relationship between the variables. We propose alterations in the procedure based on the Reversible Jump algorithm of Dobra et al. (2011) for selecting and fitting the Graphical Gaussian model. We also create indicators to evaluate simulation results from a Graphical Gaussian model. The results obtained in this work are favorable to our proposal presented, in which an improvement in the model selection method was observed, reducing the error when searching for the covariance structure.
 
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
2023-08-24
 
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.