Response surface model with some additional auxiliary variables.

Abstract

A quadratic polynomial model was studied, using response surface method, with some additional variables included in the model, in order to obtain equations to evaluate the dependent variable behavior after the inclusion of the additional variables. The parameter estimators (treatment and regression) were obtained using the least squares method. An algorithm was developed to perform the statistical analysis, considering the model adapted to a complete factorial design with three factors and three levels. In addition, estimators of variance and covariance of the parameters and variance analysis were determined.