Comparing least-squares and goal programming estimates of linear regression parameter.

Abstract

A regression model is a mathematical equation that describes the relationship between two or more variables. In regression analysis, the basic idea is to use past data to fit a prediction equation that relates a dependent variable to independent variable(s). This prediction equation is then used to estimate future values of the dependent variable. The least-squares method is the most frequently used procedure for estimating the regression model parameters. However, the method of least-squares is biased when outliers exist. This paper proposes goal programming as a method to estimate regression model parameters when outliers must be included in the analysis.