Use of statistical models to analyse
 data from oil reservoir

Rejane dos Santos BRITO[1]

Getúlio José Amorim do AMARAL[2]

§    ABSTRACT: The aim of this work, from the point of view of statistical modeling, is to analyze a dataset through the logistic regression and to propose a new model that solves a problem related to geological studies regarding oil wells. The trial for obtaining the data aims to realize the evaluation of formations, from which are defined the productive capacity and the appraisal for his backups of oil and gas. The nature of the problem lead us also to evaluate the power of classification for the proposed model with regard to the two definite groups: reservoir facies and not-reservoir facies.

§    KEYWORDS: Residuals analysis; ROC curves; classification’s models.

[1] Departamento de Estatística e Informática, Universidade Federal Rural de Pernambuco – UFRPE, CEP: 52171-900, Recife, PE, Brasil. E-mail:

[2] Departamento de Estatística, CCEN, Universidade Federal de Pernambuco -- UFPE, CEP: 50740-540, Recife, PE, Brasil. E-mail: