Modelo beta inflacionado de zeros e uns: análise bayesiana de notas no curso de estatística aplicada à engenharia

• Ano de defesa: 2017
• Autor(a) principal: Freitas Júnior, Hercílio da Silva
• Tipo de documento: Dissertação
• 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: Distribuição Beta Inflacionada de Zeros e Uns; Inferência Bayesiana; Métodos Monte Carlo via Cadeias de Markov (MCCM); Bayesian Inference; Zero and One Inflated Beta Distribution; Estatística; Probabilidade e Estatística
• Link de acesso: http://repositorio.ufla.br/jspui/handle/1/12433

This dissertation discusses an implementation of Bayesian inference on parameters of a Zero and One Inflated Beta Distribution (zoib). Data used to illustrate the proceeding were grades in Applied Statistics from Engeneering Students in second semester of 2015. Algorithms were tested in a simmulation study with different sample sizes and combinaions of parametric values. This study has shown routines are unbiased and consistent. Samples from the joint posterior distribution were drawn using Gibbs Sampler with a taylor made Gaussian random walk to yield better sampling properties for the full conditional distributions of parameters of the continuous part of the model (m and f ). The actual data analysis was carried out in 13 out of the 14 items with zeroes and ones inflation. Analysis can be done routinely to examples alike and can generate usefull insight for researchers in the applied area (educational testing).