• 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.11.2020.tde-04062020-122642
Document
Author
Full name
Fábio Prataviera
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
Piracicaba, 2020
Supervisor
Committee
Ortega, Edwin Moises Marcos (President)
Suzuki, Adriano Kamimura
Tomazella, Vera Lucia Damasceno
Title in English
The parametric and semiparametric regression models based on the generalized odd log-logistic family
Keywords in English
Censored data
Cubic spline
Cure rate
Simulation
Zero inflated
Abstract in English
In this work, several analyzes were performed through regression models considering the family of new distributions, called generalized odd log-logistic-G (GOLL-G), the distributions in this family have greater flexibility, such as functions of bimodal densities. Based on the GOLL-G family, we proposed: regression models with different regression structures; inflated semi-parametric model of zeros modeling of the parameters via penalized splines; For all the modeling approaches presented, the computational resource for the implementation of the models was software R, throughout the document as well as brief descriptions of the codes used. The results obtained in the applications show that the proposed model can be an interesting alternative, especially when the data present asymmetry and bimodality.
Title in Portuguese
Modelos de regressão parametricos e semiparametricos baseados na família generalizada odd log-logística
Keywords in Portuguese
Dados censurados
Fração de cura
Inflação de zeros
Simulação
Spline cúbico
Abstract in Portuguese
Nesse trabalho foram realizadas diferentes análises via modelos de regressão considerando a família geradora de novas distribuições, denominada de generalizada odd log-logística-G (GOLL-G). As distribuições nesta família apresentam maior flexibilidade, como por exemplo, funções de densidades bimodais. Com base na família GOLL-G, foram propostos: modelos de regressão com diferentes estruturas de regressão; modelo semi-paramétrico inflacionado de zeros modelando os parâmetros via splines penalizados; Para todas as abordagens o recurso computacional para implementação dos modelos foi o software R, sendo apresentados trechos de comandos ao longo do documento assim como breve descrições dos códigos usados. Os resultados obtidos nas aplicações mostram que o modelo proposto pode ser uma alternativa interessante, principalmente quando os dados apresentam assimetria e bimodalidade.
 
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
2020-06-05
 
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.