Advertisement

Controlling the Risk of False Positive Clinical Trials

  • Ton J. Cleophas
  • Aeilko H. Zwinderman
  • Toine F. Cleophas

Abstract

Statistical hypothesis testing is much like gambling. If, with gambling once, your chance of a prize is 5%, then, with gambling 20 times, this chance will be close to 40%. The same is true with statistical testing of clinical trials. If, with one statistical test, your chance of a significant result is 5%, then after 20 tests, it will increase to 40%. This result is, however, not based on a true treatment effect, but, rather, on the play of chance. In current clinical trials, instead of a single efficacy-variable of one treatment, multiple efficacy-variables of more than one treatment are increasingly assessed. E.g., in 16 randomized controlled trials with positive results, published in the British Medical Journal (BMJ) in 2004 (Table 1), the numbers of primary efficacy-variables varied from 4 to 13. This phenomenon introduces the statistical problem of multiple comparisons and multiple testing, which increases the risk of false positive results, otherwise called type I errors. There is no consensus within the statistical community on how to cope with this problem. Also, the issue has not been studied thoroughly for every type of variable. Clinical trials rarely adjust their data for multiple comparisons. E.g., none of the above BMJ papers did. In the previous chapter we already discussed tools which can help to control the risk of false positive results. The current chapter briefly summarizes the main methods for control in order to further emphasize the importance of this issue, and it gives additional examples.

Keywords

False Positive Result British Medical Journal Disease Activity Score Honestly Significant Difference Statistical Hypothesis Testing 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hochberg Y. A sharper Bonferroni procedure for multiple tests of significance. Biometrika 1988; 75: 800–2.MathSciNetCrossRefMATHGoogle Scholar
  2. 2.
    Fuchs HA. The use of the disease activity score in the analysis of clinical trials in reumatoid arthritis. J Rheumatol 1993; 20: 1863–6.Google Scholar
  3. 3.
    Pocock SJ. Clinical trials. A practical approach. New York, Wiley, 1988.Google Scholar
  4. 4.
    Furberg C. To whom do the research findings apply? Heart 2002; 87: 570–4.CrossRefGoogle Scholar
  5. 5.
    Julius S. The ALHATT study: if you believe in evidence-based medicine. Stick to it. Hypertens 2003; 21: 453–4.CrossRefGoogle Scholar
  6. 6.
    Cleophas GM, Cleophas TJ. Clinical trials in jeopardy. Int J Clin Pharmacol Ther 2003; 41: 51–6.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2006

Authors and Affiliations

  • Ton J. Cleophas
    • 1
    • 2
  • Aeilko H. Zwinderman
    • 3
  • Toine F. Cleophas
    • 4
  1. 1.European Interuniversity College of Pharmaceutical Medicine LyonFrance
  2. 2.Department MedicineAlbert Schweitzer HospitalDordrechtThe Netherlands
  3. 3.Department Biostatistics and EpidemiologyAcademic Medical Center AmsterdamThe Netherlands
  4. 4.Technical UniversityDelftThe Netherlands

Personalised recommendations