Mills` rule of conformity states that if, in all cases where an effect occurs, there is only one preceding C factor that is common to all of these cases, then C is the cause of the effect. According to the table in this example, the only thing you ate was the oyster. So, if we apply the rule of concordance, we conclude that eating oysters is the cause of diseases. The accompanying variation method with statistical methods that can be considered as work, is used in a large number of experimental studies where a potentially relevant factor is variable (everything that might be relevant is kept constant) to see if there is a causal link between this single factor and the effect in question. (Of course, what we consider a single experiment may include the variation of several factors, but always in such a way that the results show the effects of the variation of each factor for themselves: such an experiment is only a combination of several applications of simultaneous variation.) These methods have been the subject of two main criticisms: first, they claim that they do not set the conclusions envisaged, so that they are not conclusive evidence or evidence; and, second, that they are not useful as methods of discovery. Such criticisms have been used to support the general observation that these methods play little or no role in the study of nature and that the scientific method requires a radically different description. To see how each of the five methods works, we look at its practical application to a particular situation. Suppose that on an uneventful afternoon, the university nurse realizes that an unusual number of students suffer from severe digestive disorders. Ms. Hayes suspects of course that this symptom is due to something the students ate for lunch, and I`m sure she wants to find out.
The nurse wants to find evidence that supports the conclusion that “eat?xxxx? causes digestive disorders. Mill`s methods can help us. The type of example presented above helps to refute a critique of the existence of these methods, namely that they take for granted what is really the most important part of the procedure, namely the discovery and analysis of factors. Any given use of any of these methods presupposes an identification of the possible causes, but is not totally affected by the fact that a more detailed analysis of the factors is possible. In addition, the use of the methods themselves (in particular for the discovery of singulated causal sequences and, therefore, the disposition properties of certain things) is part of the procedure that makes it possible to further differentiate and classify factors. Similarly, the assumptions used, in particular as regards the range of possible causes allowed, can be corrected and self-corrected in combination with the methods. An erroneous assumption, coupled with observations, will likely lead to conflicting conclusions, and if this happens, we are forced to modify the hypothesis, especially to look further than we did initially to look for potentially relevant factors. . . .