Advertisement

Appropriate Analysis and Presentation of Data is a must for Good Clinical Practice

  • M. Hayran
Conference paper
Part of the Acta Neurochirurgica Supplements book series (NEUROCHIRURGICA, volume 83)

Summary

Good Clinical Practice (GCP) is defined as an international ethical and scientific quality standard for designing, conducting, monitoring, auditing, analyzing and reporting trials that involve the participation of human subjects. This paper focuses mainly on the issues that need attention at the time of statistical analysis and reporting of results. Findings from a review of published articles in Turkey are also presented. The types of variables, the distributions of variables, the number of groups compared, the dependency structure among these groups and the primary goal of the analysis determine the appropriate method to be selected for the statistical analysis. The review of a stratified sample of research articles from 60 journals published in 1992 in Turkey revealed that in 56% of the cases the statistical methods were improper or inadequate. In 15% of the articles the authors failed to select an appropriate design for the proposed aim mentioned in the manuscript. Despite the recent improvements, the necessity and the value of performing and presenting research according to the international standards remains to be assimilated better by Turkish investigators.

Keywords

Clinical trials GCP data analysis manuscript preparation. 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cochran WG (1950) The comparison of percentages in matched samples. Biometrika 37: 256–266.PubMedGoogle Scholar
  2. 2.
    Gay LR, Airasian P (2000) Qualitative research: data analysis. In: Davis KM (ed) Educational research, competencies for analysis and application, 6th edn. Prentice Hall, New Jersey, p 237.Google Scholar
  3. 3.
    Jadad A(1998) Reporting and interpreting individual trials: the essentials. In: Randomised Controlled Trials, 1st edn. BMJ Books, London, pp 61–77.Google Scholar
  4. 4.
    Friedman M (1937) The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J Am Statist Assoc 32: 675–701.CrossRefGoogle Scholar
  5. 5.
    International Conference on Harmonisation Expert Working Group (1998) ICH Guideline for good clinical practice & declaration of Helsinki, 2nd edn. Janssen Research Foundation, Belgium, p 1.Google Scholar
  6. 6.
    Kruskal WH, Wallis WA (1952) Use of ranks in one-criterion variance analysis. J Am Statist Assoc 47: 583–621.CrossRefGoogle Scholar
  7. 7.
    Mann HB, Whitney DR (1947) On a test of whether one of two random variables is stochastically larger than the other. Annals of Math Stat 18: 50–60.CrossRefGoogle Scholar
  8. 8.
    Muller KE, Curtis NB (1989) Approximate power for repeated- measures ANOVA lacking sphericity. J Am Statist Assoc 84: 549–555.CrossRefGoogle Scholar
  9. 9.
    Rosner B (2000) Fundamentals of Biostatistics, 5th edn. Dux- bury Press, Pacific Grove, California.Google Scholar
  10. 10.
    Wilcoxon F (1945) Individual comparisons by ranking methods. Biometrics 1: 80–83.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag/Wien 2002

Authors and Affiliations

  • M. Hayran
    • 1
    • 2
  1. 1.OMEGA Contract Research OrganizationAnkaraTurkey
  2. 2.OMEGA Contract Research OrganizationAnkaraTurkey

Personalised recommendations