SOLUSI KUADRAT TERKECIL MODEL REGRESI FUZZY DENGAN VARIABEL DEPENDEN FUZZY SIMETRIS

Abstract

ABSTRACT: It is known that the regression model used to analyze the crisp data. In the condition that there is uncertainty (imprecision, vagueness) on values of observed variables, then the fuzzy regression model is required. In this paper discussed a fuzzy regression model with symmetrical fuzzy dependent variable and crisp independent variables using the least squares approach. The method used to find the linear model is to minimize the distance function between observed fuzzy variables with the estimation dependent variable or the corresponding theoretical value. It is shown that the solution of this model is a generalization of the classical regression model. Further discussion is about the properties of solution of the model. Keyword: center model, spread model, fuzzy distance, iterative solution.