Experimental design and statistical analysis
The experimental design was a completely randomized 32 factorial design. The factors: were frying temperature and frying time (Temperature, X1; and frying time, X2) on three levels. Regression equations were generated for the response functions using the method of least squares. The suitability of the regression was evaluated by determining the multiple correlation coefficients (r). The experimental results were fitted to a first polynomials (or linear function, Eq. (3) or second-degree polynomial equation (or quadratic function, Eq