How Biased Are Indirect Comparisons, Particularly When Comparisons Are Made Over Time in Controlled Trials?

  • Steven A. JuliousEmail author
  • Sue-Jane Wang


Indirect comparisons are undertaken when a comparison is made between two regimens, usually where the regimens have never been given concurrently in any controlled trial investigating the same general patient population. We highlight the issues of making indirect comparisons when there has been a period of time between the studies, particularly when indirect comparison is being made to placebo. We discuss the impact of any bias in indirectly estimating any effect over placebo in context with noninferiority trials.

Key Words

Clinical trials Indirect comparisons Noninferiority Placebo creep 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hasselblad V, Kong DF. Staiistical methods fur comparison to placebo in active-control trials. Drug Inf J. 2001;25:435–449.CrossRefGoogle Scholar
  2. 2.
    Lim E, Ali Z, Ali A, et al. Indirect comparison meta-analysis of aspirin therapy after coronary surgery. Br Med J. 2003;327:1309–1313.CrossRefGoogle Scholar
  3. 3.
    Song F, Altman DG, Glenny AM, Deeks JJ. Validity of indirect comparison for estimating efficacy of competing interventions; empirical evidence from published meta-analyses. Br Med J. 2003: 326:472.CrossRefGoogle Scholar
  4. 4.
    Wang SJ, Hung HMJ, Tsong Y. Non-inferiority analysis in active controlled trials. Encyclopaedia of Biopharmaceutical Statistics, 2nd ed. New York: Marcel Dekker; 2003:674–677.CrossRefGoogle Scholar
  5. 5.
    D’Agostino RB, Massaro J, Sullivan LM. Non-inferiority trials: design concepts and issues—the encounters of academic consultants in statistics. Stat Med. 2003;22:169–186.CrossRefGoogle Scholar
  6. 6.
    Wang SJ, Hung HMJ, Tsong Y. Utility and pitfalls of some statistical methods in active controlled trials. Control Clin Trials. 2002;23:15–28.CrossRefGoogle Scholar
  7. 7.
    Snapinn SM. Alternatives for discounting in the analysis of non-inferiority trials. J Biopharm Stat. 2004;14:263–273.CrossRefGoogle Scholar
  8. 8.
    Bech P. Meta analysis of placebo controlled trials with mirtazipine using core items of the Hamilton depression scale as evidence of pure anti-depressive effect in the short term treatment of major depression. Int J Neuropsychopharmacol. 2001;4:337–345.CrossRefGoogle Scholar
  9. 9.
    Furukawa T, McGuire H, Barbui C. Low dosage tricyclic antidepressants for depression. Cochrane Database. 2003.Google Scholar
  10. 10.
    Wilson K, Motram P. Svanranthan P, Nightingale A. Antidepressants versus placebo for the depressed elderly. Cochrane Database. 2003.Google Scholar
  11. 11.
    Hazell P, O’Connel D, Heathcote D, Henry D. Tricyclic drugs Tor depression in children and adolescents. Cochrane Database. 2003.Google Scholar
  12. 12.
    Walsh BT, Sneidman SN, Sysko R, Gould M. Placebo response in studies of major depression, variable, substantial and growing. JAMA. 2002;14: 1840–1847.CrossRefGoogle Scholar
  13. 13.
    McClung C, Quessy S, Julious S, Segretti A, Blum D. Placebo response rates in geographical location in COX-2 inhibitor trials of rheumatoid arthritis (RA) and osteoarthritis (OA). Paper presented at American College of Rheumatology Conference. San Antonio, 2004.Google Scholar
  14. 14.
    CHMP. Points to consider on switching between superiority and non-inferiority. Doc CPMP/EWP/482/99. 2000. Available at: Accessed April 14, 2008.
  15. 15.
    ICH E10. Choice of control group in clinical trials. 2000. Available at: Accessed April 14, 2008.
  16. 16.
    Jones B, Jarvis P, Lewis JA, Ebbutt AF. Trials to assess equivalence: the importance of rigorous methods. Br Med J. 1996;313:36–39.CrossRefGoogle Scholar
  17. 17.
    Hung HMJ, Wang SJ, Lawrence J, O’Neil RT. Some fundamental issues with non-inferiority testing in active controlled trials. Stat Med. 2003;22:213–225.CrossRefGoogle Scholar
  18. 18.
    Wiens BL. Choosing an equivalence limit for non-inferiority and/or equivalence studies. Control Clin Trials. 2002;23:2–14.CrossRefGoogle Scholar
  19. 19.
    CHMP. Guideline on the choice of non-inferiority margin. Doc CPMP/EWP/2158/99. 2005. Available at: Accessed April 14. 2008.
  20. 20.
    Julious SA. Tutorial in biostatistics: sample sizes for clinical trials with normal data. Stat Med. 2004;23:1921–1986.CrossRefGoogle Scholar
  21. 21.
    Wang SJ, Hung HMJ, TACT method for non-inferiority testing in active controlled trials. Stat Med. 2003;22:227–238.CrossRefGoogle Scholar
  22. 22.
    Datta S, Halloran ME, Longini IM. Augmented HIV vaccine trial design for estimating reduction in infectiousness and protective efficacy. Stat Med. 1998;17:185–200.CrossRefGoogle Scholar

Copyright information

© Drug Information Association, Inc 2008

Authors and Affiliations

  1. 1.Medical Statistics Group, Health Services ResearchUniversity of SheffieldSheffieldEngland
  2. 2.Office of Biostatistics, Office of Translationat SciencesCenter for Drug Evaluation and Research, US FDASilver SpringUSA

Personalised recommendations