Regressão logística sob o ponto de vista inferencial e preditivista

Loading...
Thumbnail Image

Journal Title

Journal ISSN

Volume Title

Publisher

Universidade Federal de Juiz de Fora (UFJF)

DOI

Abstract

When building a model, we have the option of two perspectives, an inferential one, which has a greater focus on the interpretation of explanatory variables and the other that prioritizes the prediction of new observations. This work intends to present tools from both perspectives for the Logistic Regression model. For this, the estimation by maximum likelihood will be presented, tests to adjust the model, for the first case, and devices used to improve the forecast, such as Cross Validation and penalties such as Lasso and Ridge for the second case.

Description

Citation

Endorsement

Review

Supplemented By

Referenced By

Creative Commons license

Except where otherwise noted, this item's license is described as Acesso Aberto