Distribuição gama generalizada geométrica estendida

• Ano de defesa: 2015
• Autor(a) principal: Bortolini, Juliano
• Tipo de documento: Tese
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Lavras; Programa de Pós-Graduação em Estatística e Experimentação Agropecuária; UFLA; brasil; Departamento de Ciências Exatas
• Palavras-chave em Português: Análise de sobrevivência; Regressão locação-escala; Estimação de máxima verossimilhança; Inferência Bayesiana; Bimodal; Survival analysis; Location-scale regression model; Maximum likelihood estimation; Bayesian inference; Probabilidade e Estatística Aplicadas; Agronomia
• Link de acesso: http://repositorio.ufla.br/jspui/handle/1/10701

New probability distributions are proposed in order to get better fit to the complex data such as censored, skewed and bimodal. In this perspective, this work proposed new more flexible models for survival analysis. The first model proposed is the extended generalized gamma geometric distribution of five parameters, which includes well-known lifetime special sub-models such as the generalized gamma. We provided a mathematical treatment of the new distribution including explicit expressions for moments, moment generating function, mean deviations, reliability and order statistics. Further, we developed an extension of this distribution by assuming that a shape parameter can take negative values. Additionally, we derived the log-transformed distribution and its regression model. The new regression model represents a parametric family of models that includes as sub-models some widely known regression models that can be applied to censored survival data. Finally, an application of the new models to real data showed that they could provide a better fit than other statistical models frequently used in lifetime data analysis.