The model was interpreted graphically and visualized by
drawing 2D contour plots and 3D response surface plots. 2D
contour plots showed the iso-response lines as a function of the
levels of two factors, while 3D response surface plots represented
the response in a third dimension. From such plots, it was possible
to derive the optimal polymer concentrations. When three or more
factors are considered, 2D and 3D contours plots represent only a
part of the entire response surface in the experimental domain
(Dejaegher and Vander Heyden, 2011).
The statistical analysis of the data was performed by means of
Statgraphics 5.0 (Statistical Graphics Co., Rockvillle, MD, USA) and
pointed out that the best fit model for each response variable was
the quadratic one (Eq. (2)).