Determining Importance of Ranges of MMPI Scales Using Fuzzification and Relevant Attribute Selection

The paper presents an empirical study of the use of fuzzification and relevant feature selection to determination of the importance of particular ranges of MMPI scales. The importance is determined in terms of classification capabilities. MMPI (Minnesota Multiphasic Personality Inventory) is a standardized psychometric test of adult personality and psychopathology. The MMPI test delivers psychometric data in a form of the so-called profiles consisting of values of thirteen descriptive attributes (corresponding to scales). Determination of the importance of ranges of MMPI scales is crucial for computer-aided classification tasks as well as from the diagnostic point of view. The experiments were performed on a real-life data set consisting of over 1700 profiles. A special attention is focused in the paper on the fuzzification process implemented in CLAPSS (Classification and Prediction Software System). CLAPSS is a tool developed for solving different classification and prediction problems using, among others, some specialized approaches based mainly on fuzzy sets and rough sets.