Uncertain multivariable regression model

Abstract

Uncertainty theory provides an alternative to model human belief degree without the scope of probability theory. Supposing that a response variable is an uncertain variable, the simple uncertain regression has proposed. In many cases, the number of response variables is more than one. This paper proposes uncertain multivariable linear regression model which has multiple response variables. Firstly, this paper discusses generalized least squares estimate of simple uncertain linear regression model. Moreover, this paper introduces a least squares method to estimate unknown parameters of uncertain multivariable linear regression.