Measuring object similarity using the method of free clustering is gaining in popularity. Instructions are usually simple and since no structure is imposed on the subject's selection, response bias is reduced. More importantly, measures of object similarity derived from the judges' clustering can be adequately analyzed by the methods of multidimensional scaling. Subjects are usually asked to judge or select objects which are most similar and form them into groups or clusters. The number of clusters is variable and an object by itself can constitute a cluster. This paper is concerned with measuring and displaying distributions of differences between judges following free clustering. By using a computer to generate random distributions of differences, the probability distributions for various numbers of objects in a cluster were determined and are presented. Theoretical analyses are used to create general formulas for the mean and standard deviations of the differences for varying the number of objects. The results should have value for assessing interjudge reliability and for analyzing object similarity matrices since the responses of groups of different judges can be analyzed separately. (Author/RL)