Fuzzy regression methodology for crop yield forecasting using remotely sensed data

Multiple linear regression methodology is widely employed for crop yield forecasting using remotely sensed data. Here it is assumed that response variable remains same over replications for fixed values of predictor variables. In reality, response variable lies in an interval and so can not be described by a single number. In this paper, a new promising approach of "Fuzzy regression" is discussed which is capable of handling such a situation. The methodology is illustrated with help of secondary data culled from literature. It is shown that latter approach is not only superior to former but is also capable of handling highly correlated variables.