Comparação de modelo Clássico e Bayesiano para dados de óbitos perinatais no ISEA, Campina Grande-PB

Abstract

Generalized linear models are useful, among other situations, when you want to fit models to data that do not follow normality and can not be adjusted using only simple linear regression. Another powerful tool for estimation is Bayesian methods, based on conditional probabilities. In this work we present an adjustment of logistic regression models with parameters estimated by the maximum likelihood method that is updated using Bayesian inference techniques. These methods were applied to the data selected at the Instituto de Saúde Elpídio de Almenida which is located in the city of Campina Grande - PB. The information refers to pregnant patients that attended this health unit. he objective was to obtain the best possible model provide us with information about a child's chance of dying in function of maternal variables using the maximum likelihood estimation method and the Bayesian method. The adjustments and diagnoses of the models were carried out using the software R.