The problem of selecting a method for identifying homogeneous classes within a heterogeneous sample was considered. It was suggested that a definition of a class was needed to provide the basis for such a method of analysis. Thus a method was proposed which was explicitly derived from a definition. The defiition required the objects in a class to be different from objects not in the class as well as similar to each other. A comparison of the results from various samples indicated the necessity for classification methods to recognize the error in natural observations. As the size of a sample increases, so does the probability of a deviant or erroneous comparison among objects. Thus an allowance was made for 6% of the comparisons involving any object to be deviant.
No takes yet. Share an insight, caveat, or question.
Kenneth A. Carlson (1972) studied this question.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: