Divergence and Similarity of Logistic Regression and Linear Discriminant Analyses in Evaluating Factors Associated with the Prevalence of Bronchopneumonia.

Abstract

Logistic regression and Discriminant analyses are both used to forecast the probability of a certain categorical result based on numerous explanatory variables (predictors). The purpose of this study is to assess the convergence and comparability of the two models when applied to data from the health sciences. In this regard, we modeled the association of several factors with the prevalence of bronchopneumonia symptoms with both techniques and compared the result. It was observed that the logistic and discriminant analyses similarly produced the same result.