The historical approach to the interpretation of physical, chemical and biological phenomena has been to consider relationships with causative factors that can be reduced to linearity allowing simple and direct interpretation. However, it is increasingly evident that there is often more information in the data than linear interpretations allow. The current capacity for computers to assist in identifying non-linear relationships allows greater interpretation of data which illuminates the phenomena allowing the information to be translated into knowledge that can be used wisely to promote various desirable pharmaceutical outcomes. This short volume is intended to stimulate the reader to contemplate research and development areas in which the data might be more accurately interpreted to allow greater understanding and ultimately control of the pharmaceutically complex phenomena.
