FUZZY LOGISTIC REGRESSION BASED ON LEAST SQUARE APPROACH AND TRAPEZOIDAL MEMBERSHIP FUNCTION

Abstract

Logistic regression is a non-linear modification of the linear<br />regression. The purpose of the logistic regression analysis is to<br />measure the effects of multiple explanatory variables which can be<br />continuous and response variable is categorical. In real life there are<br />situations which we deal with information that is vague in<br />nature and there are cases that are not explained<br />precisely. In this regard, we have used the concept of possiblistic<br />odds and fuzzy approach. Fuzzy logic deals with linguistic<br />uncertainties and extracting valuable information from linguistic<br />terms. In our study, we have developed fuzzy possiblistic logistic<br />model with trapezoidal membership function and fuzzy possiblistic<br />logistic model is a tool that help us to deal with imprecise<br />observations. Comparison fuzzy logistic regression model with classical<br />logistic regression has been done by goodness of fit criteria on real life as an example.