The objective of much experimentation in drying is to build or discover a suitable model for a drying system. In this study, an attempt is made to formulate an approach to the problem of iteratively improving models, guided by the inefficiences of an initial tested model. This model involved both moisture diffusion coefficient and external mass transfer coefficient. A statistical analysis was applied to the residual populations created by fitting a model to the experimental data, so as to exhibit possible model inadequacies. Inspection of the tendencies produced, suggested what modifications were necessary for improvement. The cycle was repeated until an adequate model was found.