A TABLE OF EXPECTED STRESS VALUES FOR RANDOM RANKINGS IN NONMETRIC MULTIDIMENSIONAL SCALING

Abstract

The results of applying a nonmetric multidimensional scaling algorithm to sets of pseudo random data are used as the basis for constructing, by means of regression techniques, a table which will assist a user to decide whether empirically obtained data sets are the result of a random process. The table covers the range from 12 to 48 objects (points) for one to five recovered dimensions.