Premium
A METHOD OF TREATING INDIVIDUAL DIFFERENCES IN MULTI‐DIMENSIONAL SCALING *
Author(s) -
Keats J. A.
Publication year - 1964
Publication title -
british journal of statistical psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.157
H-Index - 51
eISSN - 2044-8317
pISSN - 0950-561X
DOI - 10.1111/j.2044-8317.1964.tb00242.x
Subject(s) - accommodation , psychology , preference , social psychology , scaling , distortion (music) , multidimensional scaling , politics , statistics , mathematics , computer science , political science , amplifier , computer network , geometry , bandwidth (computing) , neuroscience , law
Three studies are reported in which results obtained by analysis using the multi‐dimensional ‘unfolding’ method are compared with those obtained by multi‐dimensional scaling. Attitudes of undergraduates towards crime, political parties and types of accommodation were assessed by presenting the stimuli two at a time and asking subjects to indicate preference as well as rate the differences between each pair of stimuli. Subjects were also asked to indicate whether they liked, disliked or felt indifferent towards each of the stimuli. Samples of approximately 200, 500 and 1,000 subjects respectively were used in the three studies. Where the individual differences in attitudes were relatively small, as in the crimes data, the two methods gave equally adequate representations of the data. However in their attitudes towards political parties the students showed large individual differences and this was reflected in considerable disparity between the results obtained by the two methods. An attempt was made to combine the two methods to investigate distortion produced by strong negative attitudes and the results obtained were linked to a theory of psychological balance. This theoretical explanation seemed appropriate to the results obtained from the study of students reactions to different types of accommodation.