The Journal of Social Psychology, 1982, 116, 263-267.
A CLUSTER ANALYTIC EXPLORATION OF WHAT UNDERLIES POPULAR SOCIAL SCIENCE CONSTRUCTS*
University of New South Wales, Australia
JOHN J. RAY
A set of short scales measuring authoritarianism, dogmatism, locus of control, other-directedness, alienation, neuroticism, achievement motivation, social desirability response set, and machiavellianism was administered to a quota sample in the Sydney metropolitan area, Australia (N = 87). Under cluster analysis, the items fell into three second-order clusters identifiable as measuring personal adjustment, achievement motivation, and cynicism. It was concluded that for research to be widely noted among psychologists it probably would have to be concerned with variations on one of those three themes.
Of the many thousands of attitude and personality scales in existence, it is notable how only a very small number seem to see repeated use. One can detect that some constructs in psychology and sociology are vastly more fashionable or popular than others. In the '50s and '60s the example par excellence of this was, of course, authoritarianism measured by the California F scale. The best example currently seems to be the Rotter locus of control scale.
The present study is an attempt to see what underlies such constructs. What does it take to make a construct popular? Are the popular constructs themselves reducible to an even smaller descriptive universe? Do they have a genuine life of their own or are they only slight variations on long-known and universal themes?
The efforts of Cattell (1) and Eysenck (2) are well-known in this field. They, however, aspire to explore the whole domain of personality with a view to describing characteristic human behavior as economically as possible. The aspiration here is much different: what is attempted is to explore the interests of the psychologist himself. What do those constructs that appeal to him have in common? Unlike the aim of the work of Eysenck or Cattell, the expectation underlying the present work is that the factors revealed will not cover the whole of the person-descriptive universe.
The constructs chosen for examination were: authoritarianism, dogmatism, locus of control, other-directedness, alienation, neuroticism, achievement motivation, approval motivation (social desirability response set), and Machiavellianism.
Scales to measure these constructs were assembled and administered to a quota sample of 87 people from the population of Sydney, Australia. As some of the results from this study have already been reported elsewhere (12, 13, 14), details of the sampling and full references for the scales will not be repeated here. Suffice it to say that although the sample was small, its community-based character was thought to give it some interest when compared with the more usual sample of students.
To control for possible format effects, it was thought important that all scales be in common format. As all were available in Likert format, this was the format chosen. Because the large number of constructs would normally require a very long questionnaire with its attendant deleterious effect on response-rate (only highly co-operative people might be sampled), all scales were reduced to short forms. In all cases except that of Kassarjian's Other-Directedness scale (4), item-analyses were available to facilitate this: only the items correlating most highly with the original scale totals were chosen. Because of the uncertainty involved with the Kassarjian items, 12 of these were administered (compared with six to 10 for the other scales). Of the other scales, it should perhaps be noted that authoritarianism was measured by a behavior inventory [the Ray "Directiveness" scale (11)] rather than by the more usual (but less valid) attitude scale and that alienation was measured by the Ray "GA" scale (10). This latter scale represents a distillation from the sum total of all published items said to measure alienation or some related construct that could be found in the published literature.
The 86 scale items were subjected to cluster analysis which is preferred to factor analysis for the reasons given at some length in Ray (8): in general it yields factors that are more easily interpretable.
Only three second-order clusters emerged. These were subjected to conventional Likert scale item analysis to obtain criteria for how central each item was to the cluster as a whole. Weakly loading items (items showing a low item-total correlation) were deleted from further consideration in order to help sharpen the conceptual identity of each cluster. When this was done, three quite reliable scales emerged which rather clearly measured Personal Adjustment, Achievement Motivation, and Cynicism. Their coefficient "alpha" reliabilities were, respectively, .84, .77, and .78. The lengths of these scales were decided by the point in the iterative item analysis at which reliability ("alpha") ceased to rise: if further weak items had been deleted, the reliabilities would have been less and if further weak items had been retained the reliability would also have been less. See Ray (7).
The cluster analytic technique employed above is an extremely simple one, well justifying its name as "Elementary factor analysis" (5). It uses the highest correlation coefficient in each vector of the zero order matrix and, as such, does not even give "loadings" for each item. It gives only the information of how many clusters there are and which cluster each item fits best. To remedy this lack of loadings, each cluster was treated as a summative scale and subjected to standard item-analysis techniques. The item-to-total correlations become thus equivalent to centroid loadings.
Although much less popular than factor analysis, cluster analysis has many devotees who claim that it gives clearer, more "interpretable" results (e.g., 3, 6, 15). The present results would seem to represent further vindication for that claim, since the structure revealed is certainly very easily identifiable. One explanation might be that the method used above has some claims to being less affected by the problem of "error correlation." Ordinary factor analysis must try to make sense of all the correlations in the matrix, many of which contain very little "true" variance and all of which contain at least some "error" variance. By using only the highest correlations, the McQuitty method would seem to maximize the chances of the analysis being based only on correlations which had at least some "true" variance. The normal way of dealing with the error variance problem in factor analysis is to advocate that N should be large, thus maximizing the chances that error variance will be randomized out. Because, on the above reasoning, the McQuitty method has other means of dealing with the error problem, the N planned for on the present occasion could reasonably be small. The results would seem to justify the view that a large N was not required to give a clear and theoretically meaningful structure.
Although intended solely as an exploratory study, the present work can be seen as giving some support to the view that the constructs popular among social psychologists tend to be little more than ponderous relabellings of quite simple and familiar concepts. Thus the California F scale might be regarded as just another conservatism scale (9) and the I-E scale as just a "belief in luck" scale. Achievement motivation could more simply be called "ambition." Such simplifications will of course not readily secure assent, but by empirically pulling apart many different scales and rearranging their items in three simple, easily recognizable groups, the present results show that they are indeed possible.
What, then, if anything, do the present results suggest about the interests of the social scientist? Conceivably, it tells us that he is achievement motivated, fascinated by personal adjustment/maladjustment, and probably rather cynical in his beliefs about the world around him. To claim this, however, is to assume that what captures his interest are things that are of personal concern to him, that people who are interested in ambition will be ambitious, etc. The converse, of course, may be true. One may be fascinated by a phenomenon that one does not share in.
The three themes demonstrated in the present analysis may also serve as a guide to the sorts of studies of interest to one's colleagues. The value of this diagnosis in the era of grantsmanship and publish-or-perish is probably obvious if we are in some indecision about where to direct our research activities. Projects concerned with some variation on one of the three themes of achievement motivation, adjustment/maladjustment or cynicism/trust are likely to receive the warmest reception.
1. CATTELL, R. B. Personality and Motivation: Structure and Measurement. New York: World Book, 1957.
2. EYSENCK, H. J. Manual of the Maudsley Personality Inventory. London: Univ. London Press, 1959.
3. GRAY, D. B., & REVELLE, W. A cluster analytic critique of the multifactor racial attitude inventory. Psychol. Rec., 1972, 22, 103-112.
4. KASSARJIAN, W. M. A study of Riesman's theory of social character. Sociometry, 1962, 25, 213-230.
5. McQUITTY, L. C. Elementary factor analysis. Psychol. Rep., 1961, 9, 71-78.
6. PARKER, S. R., & BYNNER, J. M. Correlational analysis of data obtained from a survey of shop stewards. Hum. Relat., 1970, 23, 345-359.
7. RAY, J.J. (1972) A new reliability maximization procedure for Likert scales. Australian Psychologist 7, 40-46.
8. RAY, J.J. (1973a) Factor analysis and attitude scales. Australian & New Zealand Journal of Sociology 9(3), 11-13.
9. RAY, J.J. (1973b) Conservatism, authoritarianism and related variables: A review and an empirical study. Ch. 2 in: G.D. Wilson (Ed.) The psychology of conservatism London: Academic Press.
10. RAY, J.J. (1974) Who are the alienated? Ch. 52 in Ray, J.J. (Ed.) Conservatism as heresy Sydney: A.N.Z. Book Co.
11. RAY, J.J. (1976) Do authoritarians hold authoritarian attitudes? Human Relations, 29, 307-325.
12. RAY, J.J. (1979) The authoritarian as measured by a personality scale Solid citizen or misfit? J. Clinical Psychology 35, 744-746.
13. RAY, J.J. (1979) Is the Dogmatism scale irreversible? South African Journal of Psychology 9, 104-107.
14. RAY, J.J. (1980) Belief in luck and locus of control. Journal of Social Psychology, 111, 299-300.
15. RUMP, E. E. Cluster analysis of personal questionnaires compared with principal components analysis. Brit. J_. Soc. Clin. Psychol., 1974, 13, 283-292.
School of Sociology, The University of New South Wales P.O. Box 1, Kensington, New South Wales, Australia 2033
* Received in the Editorial Office, Provincetown, Massachusetts, on April 24, 1981. Copyright, 1982, by The Journal Press.
The new personal adjustment scale
(Cluster 1 with poorly loading items removed) Items marked 'R' are reverse-scored. All items were answered "Yes", "?" or "No" (scored 3, 2, 1). Before each item is given the scale from which it originated (AO for Achievement Orientation; AL for Alienation; DIR for Directiveness (authoritarianism); SD for Social Desirability; OD for Other-Directedness; IE for Internal/External locus of control; M for Machiavellianism and D for Dogmatism)
1. N Do you sometimes feel happy, sometimes depressed, without any apparent
2. N Are you inclined to be moody? R
3. SD Are you always willing to admit when you make a mistake?
4. AL Can you normally do what you want to in today's set-up?
5. AL The decisions of our courts of justice are as fair to a poor man as
to a wealthy man.
6. N Do you have frequent ups and downs in mood, either with or without
apparent cause? R
7. SD Do you sometimes try to get even rather than forgive and forget? R
8. SD Do you sometimes feel resentful when you don't get your own way? R
9. N Are you frequently "lost in thought"' even when you are supposed to
be taking part in a conversation? R
10. N Are you sometimes bubbling over with energy and sometimes very sluggish? R
11. AO Are you inclined to read of the successes of others rather than go out
and do the work of making yourself a success? R
12. AL Most members of Parliament and city councillors are sympathetic people
and do a good job.
13. AL In this society, most people can find contentment.
14. AL Our community is an easy and present place to live in.
15. DIR Do you find it difficult to make up your own mind about things? R
16. AO would you describe yourself as being lazy? R
17. IE Do you believe that in the long run people get the respect they deserve
in this world?
18. M Do you believe that in all cases honesty is the best policy?
19. IE Do you believe that how many friends you have depends simply on
how nice a person you are?
20. M Do you think that most people are basically good and kind?
21. IE Do you think that many times in life one might just as well decide
what to do by flipping a coin? R
22. OD Are you perfectly happy when you are left on your own?
23. SD Are you quick to admit making a mistake?
24. SD Have there been occasion when you took advantage of someone? R
25. D The "one true faith" is a myth. R
26. D It is annoying to listen to a speaker or teacher who seems unable to
make up his mind about what he really believes.
The new achievement motivation scale
(Cluster 2 with poorly loading items removed)
1. AO Is being comfortable more important to you than getting ahead? R
2. AO Are you satisfied to be no better than most other people at your job.? R
3. AO Have you always worked. hard in order to to be among the best in your
4. DIR Are you often critical of the way other people do things?
5. DIR Does incompetence irritate you?
6. AO Do you tend to plan ahead for your job or career?
7. AO Is "getting on in life" important to you?
8. DIR Do you dislike having to tell other what to do? R
9. AO Are you an ambitious person?
10. DIR Would you rather take orders than give them? R
11. DIR If anyone is going to be Top Dog, would you rather it be you?
12. AO Are you inclined to take life as it comes without much planning? R
13. IE Do you think that becoming a success is a matter of hard work -- with
luck having little or nothing to do with it?
14. OD Do you think you would be happy about it if you became a famous person?
The new Cynicism scale
(Cluster 3 with poorly loading items removed)
1. AL Beneath the polite and smiling surface of man's nature is a bottomless
pit of evil.
2. AL These days a person doesn't really know whom he can count on.
3. DIR Are you the sort of person who always likes to get their own way?
4. AO Do you take trouble to cultivate people who may be useful to you in
5. N Does your mind often wander while you are trying to concentrate?
6. AL Life today is a difficult and dangerous business and it is a matter of
chance who gets on top.
7. M Do you think the best way to handle people is to tell them what they
want to hear?
8. OD Do you believe that one is better off keeping work and social activities
9. OD In deciding whom you would prefer as a leader of some group you were in, would you prefer someone who is about average in ability at the group's
activity but who had an especially pleasing personality?
10. M Do you think that anyone who completely trusts anyone else is asking
11. M Do you think that it is hard to get ahead without cutting corners here and
12. M Do you think that it is safest to assume that all people have a vicious
streak and that it will come out when they are given a chance?
13. IE Do you think that most people don't realize the extent to which their
lives are controlled by accidental happenings?
14. M Do you think it wisest never to tell anyone the real reason you did
something unless it is useful to do so?
15. OD On the subject of social living, do you think that one should be careful
to live up to the prevailing standards of those around you?
16. IE As far as world affairs are concerned, do you think most of us are victims
of forces we can neither understand nor control?
17. IE Do you think that who gets to be boss often depends on who was lucky
enough to be in the right place first?
18. D Man on his own is a helpless and miserable creature.
19. D In these present days, everyone should look to their own happiness.
20. D Of all the different philosophies that exist in the world, there is
probably only one which is correct.
Replication is one of the cornerstones of science. A new research result will normally require replication by later researchers before the truth and accuracy of the observation concerned is generally accepted. If a result is to be replicated, however, careful specification of the original research procedure is important.
In questionnaire research it has been my observation that the results are fairly robust as to questionnaire format. It is the content of the question that matters rather than how the question is presented (But see here). It is nonetheless obviously desirable for an attempted replication to follow the original procedure as closely as possible so I have given here samples of how I presented my questionnaires in most of the research I did. On all occasions, respondents were asked to circle a number to indicate their response.
Go to Index page for this site
Go to John Ray's "Tongue Tied" blog (Backup here)
Go to John Ray's "Dissecting Leftism" blog (Backup here)
Go to John Ray's "Australian Politics" blog (Backup here)
Go to John Ray's "Gun Watch" blog (Backup here)
Go to John Ray's "Education Watch" blog (Backup here)
Go to John Ray's "Socialized Medicine" blog (Backup here)
Go to John Ray's "Political Correctness Watch" blog (Backup here)
Go to John Ray's "Greenie Watch" blog (Backup here)
Go to John Ray's "Leftists as Elitists" blog (Not now regularly updated)
Go to John Ray's "Marx & Engels in their own words" blog (Not now regularly updated)
Go to John Ray's "A scripture blog" (Not now regularly updated)
Go to John Ray's recipe blog (Not now regularly updated -- Backup here)
Go to John Ray's Main academic menu
Go to Menu of recent writings
Go to John Ray's basic home page
Go to John Ray's pictorial Home Page (Backup here)
Go to Selected pictures from John Ray's blogs (Backup here)
Go to Another picture page (Best with broadband)