The purpose of this paper is to show which models, uncertain or certain, simple or complicated, are more suitable when they are faced with incomplete information and inaccurate data.
The characteristics of fuzzy mathematics, grey system theory, rough set theory and the basic characteristics of incomplete information and inaccurate data in uncertain systems are analysed.
The similarities and differences among fuzzy mathematics, grey system theory, rough set theory and probability statistics are compared. The principle of simplicity of scientific theories, methods, and models are discussed.
It is suggested that the tendency to concentrate on a complicated model isn't always necessary when faced with the condition of incomplete information and inaccurate data.
The paper shows that a more satisfied result can be obtained with an uncertain model than with a meticulous model on a certain situation.
