Hostname: page-component-8448b6f56d-m8qmq Total loading time: 0 Render date: 2024-04-17T07:40:15.965Z Has data issue: false hasContentIssue false
  • English
  • Français

Multivariate Analysis: The Need for Data, and other Problems

Published online by Cambridge University Press:  29 January 2018

B. S. Everitt
B. S. Everitt*
Affiliation:
Biometrics Units Institute of Psychiatry, De Crespigny Park, London, SE5 8AF
Get access Rights & Permissions [Opens in a new window]

Summary

Multivariate analyses are an aid to, not a substitute for critical thinking in the area of data analysis. Meaningful results can only be produced by these methods if careful consideration is given to questions of sample size, variable type, variable distribution etc., and accusations of subjectivity in interpretation can only be overcome by replication.

The computer revolution has produced many problems for statisticians, not least of which is the ease with which experimenters may access packages of programs for multivariate analysis, and so bypass a ‘difficult’ (by which is meant one who will not do simply as he is told) statistician. Of course there are many abuses of univariate statistical methods. Here, however, the abuses are not likely to lead to such seriously misleading results as in the multivariate case.

Perhaps a major cause of the continuing misuse of statistical methods is the insistence of many journal editors in psychology and related areas, on articles being laced with multivariate analyses, and on encouraging the pedantic use of significance levels, i.e. the inevitable p < —, as if such inclusions lent an air of respectability to their journal which it might not otherwise have had. Research workers in these fields would be better encouraged to devote more time to an initial screening of their data using simple graphical techniques, to ensure that their data are at least approximately suitable for more complicated multivariate analyses.

Type
Research Article
Information
The British Journal of Psychiatry , Volume 126 , Issue 3 , March 1975 , pp. 237 - 240
Copyright
Copyright © Royal College of Psychiatrists, 1975 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Anscombe, F. J. (1960) Rejection of outliers. Technometrics, 2, 123–46.CrossRefGoogle Scholar
Everitt, B. S. (1972) Cluster analysis: a brief discussion of some of the problems. Brit. J: Psychiatry, 120, 143–5.Google ScholarPubMed
Everitt, B. S. (1974) Cluster Analysis. Heinemann Educational Books.Google Scholar
Finney, D. J. (1974) Problems, data and inference: The address of the President. J. Roy. Stats. Soc., Series A, 137, 1–22.CrossRefGoogle Scholar
Gnanadesikan, R. & Wilk, M. B. (1969) Data analytic methods in multivariate statistical analysis. In Multivariate Analysis (ed. Krishnaian, P. R.), pp. 593–638. New York: Academic Press.Google Scholar
Gorsuch, R. L. (1974) Factor Analysis. W. B. Saunders Co.Google Scholar
Horn, J. L. (1967) On subjectivity in factor analysis. Educational and Psychological Measurement, 27, 811–20.CrossRefGoogle Scholar
Kruskal, W. H. (1960) Some remarks on wild observations. Technometrics, 2, 1–3.CrossRefGoogle Scholar
Maxwell, A. E. (1972) Difficulties in a dimensional description of symptomatology. Brit. J. Psychiat, 121, 19–26.CrossRefGoogle Scholar
Paykel, E. S. (1972) Depressive typologies and response to amitriptyline. Brit. J. Psychiatry, 120, 147–56.CrossRefGoogle ScholarPubMed
Williams, W. T. & Dale, M. B. (1965) Fundamental problems in numerical taxonomy. In Advances in Botanical Research (ed. Preston, R. D.). London: Academic Press.Google Scholar
Submit a response

eLetters

No eLetters have been published for this article.