Cure rate models: alternatives methods to estimate the cure rate

Detalhes bibliográficos
Ano de defesa: 2020
Autor(a) principal: Rodrigues, Juliana Scudilio
Orientador(a): Tomazella, Vera Lucia Damasceno lattes
Banca de defesa: Não Informado pela instituição
Tipo de documento: Tese
Tipo de acesso: Acesso aberto
Idioma: eng
Instituição de defesa: Universidade Federal de São Carlos
Câmpus São Carlos
Programa de Pós-Graduação: Programa Interinstitucional de Pós-Graduação em Estatística - PIPGEs
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Português:
Palavras-chave em Inglês:
Área do conhecimento CNPq:
Link de acesso: https://repositorio.ufscar.br/handle/20.500.14289/13269
Resumo: Cure rate models in survival data studies has formed an important field in the area and has attracted the attention of researchers. In the search for new models of cure rate, the objective of this work is to propose alternative methods to model the cure rate. For this two methods are presented. The first use the methodology of the defective models and the last method use the concept the distributions family. Then, in the first method propose the defective models induced by a frailty term. Defective models have the advantage of modeling the proportion of cured without adding any extra parameters in the model, in contrast to the most models from the literature. Models with a frailty term incorporate an unobserved heterogeneity among individuals and this incorporation brings advantages for the estimated model, because it incorporates the influence of unobserved covariates in a proportional hazard model. It is showed that the new defective distributions are induced when using the gamma frailty term. The last method proposed in this work, is to use distribution families to calculate the cure rate. For this, a parameter $"p"$ is included in the Beta-G family in order to create a new family of cure rate models, the new family can be more flexible for modeling cure rate than the standard mixture models.