dual scaling
(DS) a method of assessing relationships and patterns among categorical data that involves assigning scale values to the elements of the data set. For example, DS may be useful when assessing the relationship between achievement motivation and performance. When achievement motivation is low or high, performance is expected to be low; however, when achievement motivation is moderate, performance is expected to be high. This curvilinear relationship can be analyzed more effectively with DS than with conventional statistical methods (e.g., correlation, regression), as the latter require assumptions of linearity and would reveal no apparent association between the variables. Also called optimal scaling.