Hostname: page-component-78c5997874-8bhkd Total loading time: 0 Render date: 2024-11-09T15:43:21.275Z Has data issue: false hasContentIssue false
  • English
  • Français

Classifications of the elderly population

Published online by Cambridge University Press:  14 November 2008

I. T. Jolliffe ,
B. Jones ,
M. R. J. Knapp  and
B. J. T. Morgan
I. T. Jolliffe
Affiliation:
Mathematical Institute, University of Kent at Canterbury, Canterbury, Kent, England.
B. Jones
Affiliation:
Mathematical Institute, University of Kent at Canterbury, Canterbury, Kent, England.
M. R. J. Knapp
Affiliation:
Personal Social Services Research Unit, University of Kent at Canterbury.
B. J. T. Morgan
Affiliation:
Mathematical Institute, University of Kent at Canterbury, Canterbury, Kent, England.
Get access Rights & Permissions [Opens in a new window]

Abstract

To the existing ways of categorizing elderly individuals we here add a reasonably objective approach using recent survey data and statistical methods of multivariate analysis. The groupings obtained have been surprisingly clear-cut, so that simple rules can be devised for discriminating between clusters. We suggest this analysis as a useful way of gleaning information about elderly people, information which may help in the efficient allocation of services.

Type
Research Article
Information
Ageing & Society , Volume 2 , Issue 3 , November 1982 , pp. 331 - 355
Copyright
Copyright © Cambridge University Press 1982

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

NOTES

1 Hunt, A., The Elderly at Home: A Study of People Aged 65 and Over Living in the Community in England in 1976, Office of Population Censuses and Surveys, Social Survey Division, London, HMSO, 1978.Google Scholar

2 Ibid.

3 Jolliffe, I. T., Jones, B. and Morgan, B. J. T., ‘Cluster analysis of the elderly at home: a case study’, In Data Analysis and Informatics, Editors Diday, E., 1980, 745–57, North-Holland, Amsterdam.Google Scholar

4 Hunt, , op. cit., p. 4.Google Scholar

5 A good introductory account of principal component analysis for readers unfamiliar with the technique may be found in: Morrison, D. F., Multivariate Statistical Methods, (and Edition), McGraw-Hill, Kogakusho, Tokyo, 1976.Google Scholar

6 Principal component analysis may be done using either covariances or correla tions between variables. In the former case, linear combinations of the original variables as they stand are considered; in the latter, linear combinations of the variables standardised to have unit variance are used. In what follows, the principal components are derived using correlations. This is because it is inad visable to use covariances when different variables are measured in different units (e.g. age, persons/room) and particularly when some of the variables are qualitative (e.g. sex).

7 Krzanowski, W. J. ‘Between-groups comparison of principal components’. Journal of the American Statistical Association, 74, 1979, 703–7.CrossRefGoogle Scholar

8 Moser, C. A. and Scott, W., British Towns, Oliver & Boyd, Edinburgh, 1961.Google Scholar

9 Jolliffe, I. T., Jones, B. and Morgan, B. J. T., An approach to assessing the needs of the elderly, Clearing House for Local Authority Social Services Research, No. 2, 04, 1982a, pp. 1–102.Google Scholar

10 Jolliffe, , op. cit., 1980.Google Scholar

11 Jolliffe, , op. cit., 1982a.Google Scholar

12 Jolliffe, I. T., Jones, B. J. and Morgan, B. J. T., ‘Utilising clusters: a case-study involving the elderly’, Journal of the Royal Statistical Society, Series A, 145, 1982, 224–36.CrossRefGoogle Scholar

13 Morrison, D. F., op. cit.Google Scholar

14 Nie, N. H., Hull, C. H., Jenkins, J. G., Steinbrenner, K. and Best, D. H., Statistical Package for the Social Sciences, McGraw-Hill, New York, 1975.Google Scholar

15 Stone, M., ‘Cross-validatory choice and assessment of statistical predictions’, Journal of the Royal Statistical Society, Series B, 36, 1974, pp. 111–47.Google Scholar

16 Jolliffe, I. T., Jones, B. and Morgan, B. J. T. ‘An approach to assessing the needs of the elderly’, Municipal Journal, 19 09 1980, pp. 1121–2.Google Scholar

17 Jolliffe, I. T., op. cit., 1982a.Google Scholar

18 It was not the intention of this study to explore these relationships rigorously. Rather, our comments are included merely to suggest both the utility of cluster analysis and the nature of the associations between variables. Note that the com ments made are based on the greater detail of the reference of note 17, and only partly on Tables 5 and 6. This is especially true with respect to the ‘income’ variable, for which there are problems both of definition and of division. Full details are in the reference of note 17. Recent British research has confirmed the complexity of these and other associations. See, for example: Abrams, M.; Beyond Three Score Years and Ten, Age Concern, London, 1978;Google ScholarTownsend, P., ‘The structured dependency of the elderly: a creation of social policy in the twentieth century’, Ageing and Society, 1, 1981, pp. 5–28;CrossRefGoogle ScholarWalker, A., ‘Towards a political economy of old age’, Ageing and Society, 1, 1981, pp. 73–94.CrossRefGoogle Scholar

19 See, for example, Abrams, , op. cit.Google Scholar, and Abrams, M., ‘Subjective social indicators’, Social Trends, 4, 1973, pp. 35–50.Google Scholar

20 Bebbington, A. C. and Davies, B. P., ‘Territorial need indicators: a new approach – Part I and II’, Journal of Social Policy, 9, 1980, pp. 145–68 and 433–62.CrossRefGoogle Scholar

21 Ibid.

22 Taylor, R. and Ford, G., ‘Lifestyle and ageing’, Ageing and Society, I, 1981, pp. 329–45.CrossRefGoogle Scholar

23 See, for example, Erickson, E. P., ‘A regression method for estimating population changes of local areas’, Journal of the American Statistical Association, 69, 1974, pp. 867–75;CrossRefGoogle ScholarHenmann, L. F., Identifying the Housing and Support Service Needs of the Semi-Independent Elderly: Towards a Descriptive Planning Model for the Area Agencies on Ageing in Illinois, Housing Research and Development, University of Illinois, 1977;Google ScholarBebbington, and Davies, , op. cit.Google Scholar

24 Bebbington, and Davies, , op. cit., p. 438.Google Scholar A similar approach to the allocation of health service resources from central government to the area health authorities is described by West, P. A., ‘Theoretical and practical equity in the NHS’, Social Science and Medicine, 150, 1981, pp. 117–22.Google Scholar

25 Note that these approaches are not new in that they are employed in, e.g., Manchester's Old People: a study for the social service department: Local Government Operational Research Unit, Report No. C.120, 1972. However, the cluster analysis methodology used here is an improvement on that used previously:

26 Curtis, S. E., ‘Spatial analysis of surgery locations in general practice’, Social Science and Medicine, 16, 1982, pp. 303–13;CrossRefGoogle ScholarPubMed and Curtis, S. E., ‘Spatial access, need and equity: an analysis of the accessibility of primary health facilities for the elderly in East Kent’, unpublished Ph.D. thesis, University of Kent at Canterbury, 1980.Google Scholar

27 Curtis, , op. cit., 1982, p. 303.Google Scholar

28 Carter, J., Day Services for Adults, Allen and Unwin, London, 1981;Google ScholarEdwards, C., Gorbach, P. and Sinclair, I., ‘Day Centres for the elderly: variations in type, provision, and user response’, British Journal of Social Work, 10, 1980, pp. 419–30.Google Scholar

29 Jones, B., ‘Cluster analysis of some social survey data’, B.I.A.S., 6, 1979, 25–6.Google Scholar