Statistical Methods for Measuring Outcomes

  • Graham Dunn

Abstract

This book concerns promotion of the routine use of outcome measures in clinical practice; the purpose of this chapter, however, is to warn care providers to think very very carefully before routinely using such measures. Just what are the benefits of their use? What are the outcome measures intended to demonstrate? In order to try to convince the reader that there might be real difficulties in the interpretation of the results, the main body of the paper concentrates on the difficulties in the interpretation of data from a structured research project that has been specifically designed to evaluate an innovation in mental health care provision. The difficulties of interpreting haphazardly collected data as part of routine clinical or administrative practice will be far greater. One of the main purposes of an evaluative exercise is comparison: which approach to service provision is the better? If care providers really want to be involved in mental health service evaluation then their time would be much better spent in taking part in a large multicentre trial.

Keywords

Placebo Covariance Assure Stratification Stein 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Buck C, Donner A (1982) The design of controlled experiments in the evaluation of non-therapeutic interventions. J Chronic Dis 35: 531–538PubMedCrossRefGoogle Scholar
  2. Cochran WG (1983) Planning and analysis of observational studies. Wiley, Chichester New YorkCrossRefGoogle Scholar
  3. Collett D (1991) Modelling binary data. Chapman & Hall, LondonGoogle Scholar
  4. Cook TD, Campbell TD (1979) Quasi-experimentation: design and analysiss issues for field settings. Houghton-Mifflin, BostonGoogle Scholar
  5. Cornfield J (1978) Randomization by group: a formal analysis. Am J Epidemiol 108:100–102PubMedGoogle Scholar
  6. Day SJ, Graham DF (1991) Sample size estimation for comparing two or more treatment groups in cHnical trials. Stat Med 10: 33–43PubMedCrossRefGoogle Scholar
  7. Donner A, Klar N (1993) Confidence interval construction for effect measures arising from cluster randomization trials. J Clin Epidemiol 46: 123–131PubMedCrossRefGoogle Scholar
  8. Donner A, Brown KS, Brasher P (1990) A methodological review of non-therapeutic intervention trials employing cluster randomization, 1979–1989. Int J Epidemiol 19: 795–800PubMedCrossRefGoogle Scholar
  9. Duffy SW, South MC, Day NE (1992) Cluster randomization in large public health trials: the importance of antecedent data. Stat Med 11: 307–316PubMedCrossRefGoogle Scholar
  10. Dunn G (1989) Design and analysis of reliability studies: the statistical evaluation of measurement errors. Edward Arnold, LondonGoogle Scholar
  11. Dunn G (1992) Design and analysis of rehability studies. Stat Methods Med Res 1:123–157PubMedCrossRefGoogle Scholar
  12. Fleiss JL (1987) Design and analysis of clinical experiments. Wiley, Chichester New YorkGoogle Scholar
  13. Gardner MJ, Ahman DC (1989) Statistics with confidence. BMJ, LondonGoogle Scholar
  14. Goldstein H (1987) Multilevel models in educational and socid research. Griffin, LondonGoogle Scholar
  15. Greenwood RJ, McMillan TM, Brooks DN, Dunn G, Brock D, Dinsdale S, Murphy LD, Price JR (1994) An investigation into the effects of case management after severe head injury. BMJ 308:1199–1205PubMedCrossRefGoogle Scholar
  16. Hill AB (1955) Introduction to medical statistics, 5th edn. (Monograph) Lancet LondonGoogle Scholar
  17. Hsieh FY (1988) Sample size formulae for intervention studies with the cluster as unit of randomization. Stat Med 8:1195–1201CrossRefGoogle Scholar
  18. Hurlbert SH (1984) Pseudoreplication in the design of ecological field experiments. Ecol Monogr 54: 187–211CrossRefGoogle Scholar
  19. Johnson AL (1989) Methodology of cHnical trials in psychiatry. In: Freeman C, Tyrer P (eds) Research methods in psychiatry. Royal College of Psychiatrists, London, pp 12–45Google Scholar
  20. Lachin JM (1981) Introduction to sample size determination and power analysis for cHnical trials. Controlled Clin Trials 2: 93–113PubMedCrossRefGoogle Scholar
  21. Manly BFJ (1992) The design and analysis of research studies. Cambridge University Press, CambridgeGoogle Scholar
  22. Pocock S (1983) Clinical trials: a practical approach. Wiley, Winchester New YorkGoogle Scholar
  23. Shipley MJ, Smith PG, Dramaix M (1989) Cdculation of power for matched pair studies when randomization is by group. Int J Epidemiol 18: 457–461PubMedCrossRefGoogle Scholar
  24. Spitzer WO, Feinstein AR, Sackett DL (1975) What is a health care trial? J Am Med Assoc 233:161–163CrossRefGoogle Scholar
  25. Streiner DL, Norman GR (1989) Health measurement scales: a practical guide to their development and use. Oxford University Press, OxfordGoogle Scholar
  26. Wright JG, Feinstein AR (1992) A comparative contrast of cUnimetric and psychometric methods for constructing indexes and rating scales. J Clin Epidemiol 45:1201–1218PubMedCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Graham Dunn
    • 1
  1. 1.Department of Biostatistics and ComputingInstitute of PsychiatryLondonUK

Personalised recommendations