, Volume 29, Issue 2, pp 87–96 | Cite as

Consistently Estimating Absolute Risk Difference when Translating Evidence to Jurisdictions of Interest

  • Simon EckermannEmail author
  • Michael Coory
  • Adrew R. Willan
Leading Article Consistently Estimating Risk Difference


Economic analysis and assessment of net clinical benefit often requires estimation of absolute risk difference (ARD) for binary outcomes (e.g. survival, response, disease progression) given baseline epidemiological risk in a jurisdiction of interest and trial evidence of treatment effects. Typically, the assumption is made that relative treatment effects are constant across baseline risk, in which case relative risk (RR) or odds ratios (OR) could be applied to estimate ARD. The objective of this article is to establish whether such use of RR or OR allows consistent estimates of ARD.

ARD is calculated from alternative framing of effects (e.g. mortality vs survival) applying standard methods for translating evidence with RR and OR. For RR, the RR is applied to baseline risk in the jurisdiction to estimate treatment risk; for OR, the baseline risk is converted to odds, the OR applied and the resulting treatment odds converted back to risk.

ARD is shown to be consistently estimated with OR but changes with framing of effects using RR wherever there is a treatment effect and epidemiological risk differs from trial risk. Additionally, in indirect comparisons, ARD is shown to be consistently estimated with OR, while calculation with RR allows inconsistency, with alternative framing of effects in the direction, let alone the extent, of ARD.

OR ensures consistent calculation of ARD in translating evidence from trial settings and across trials in direct and indirect comparisons, avoiding inconsistencies from RR with alternative outcome framing and associated biases. These findings are critical for consistently translating evidence to inform economic analysis and assessment of net clinical benefit, as translation of evidence is proposed precisely where the advantages of OR over RR arise.


Relative Risk Natalizumab Consistent Estimation Binary Outcome Baseline Risk 
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.



The authors thank Lloyd Sansom and the Pharmaceutical Benefits Advisory Committee (PBAC) for encouraging improvements in methods for translating evidence during processes of PBAC guideline revision, evaluation and working committees from 2005 to 2010 and the 2006 PBAC Workshop run by Professors Willan and Eckermann. The authors also thank the European International Society for Pharmacoeconomics and Outcomes Research (ISPOR) for the opportunity to present an early version of the paper in Athens 2008, and participants at the 2008 (Barossa Valley) and 2009 (Oxford) Health Economics from Theory to Practice courses for useful feedback. Finally, the authors acknowledge the constructive comments of anonymous reviewers at PharmacoEconomics in improving the paper. Naturally, any remaining errors or omissions remain the responsibility of the authors.

The data, models and methodology used in this research are not subject to any proprietary interests. A.R. Willan is funded by the Discovery Grant Program of the Natural Sciences and Engineering Research Council of Canada (grant number 44868-08). No sources of funding were used to assist in the preparation of this article. The authors have no conflicts of interest that are directly relevant to the content of this article.


  1. 1.
    Engels EA, Schmid CH, Terrin N, et al. Heterogeneity and statistical significance in meta-analysis: an empirical study of 125 meta-analyses. Stat Med 2000; 19 (13): 1707–28PubMedCrossRefGoogle Scholar
  2. 2.
    Deeks J. Issues in the selection of a summary statistic for meta-analysis of clinical trials with binary outcomes. Stat Med 2002; 21: 1575–600PubMedCrossRefGoogle Scholar
  3. 3.
    Furukawa T, Guyatt G, Griffith L. Can we individualize the ‘number needed to treat’? An empirical study of summary effect measures in meta-analyses. Int J Epidemiol 2002; 31: 72–6Google Scholar
  4. 4.
    Sinclair J, Bracken M. Clinically useful measures of effect in binary analyses of randomised trials. J Clin Epidemiol 1994; 47: 881–9PubMedCrossRefGoogle Scholar
  5. 5.
    Davies H, Crombie I, Travokoli M. When can odds ratios mislead? BMJ 1998; 316: 989–91PubMedCrossRefGoogle Scholar
  6. 6.
    Sackett DL, Deeks JJ, Altman DG. Down with odds ratios! Evid Based Med 1996; 1: 164–6Google Scholar
  7. 7.
    Sheps M. Shall we count the living or the dead? N Engl J Med 1958; 259: 1210–4PubMedCrossRefGoogle Scholar
  8. 8.
    Walter S. Choice of effect measure for epidemiological data. J Clin Epidemiol 2000; 53: 931–9PubMedCrossRefGoogle Scholar
  9. 9.
    Fleiss J. Measures of effect size for categorical data. In: Cooper H, Hedges L, editors. The handbook of research synthesis. New York: Russell Sage, 1994Google Scholar
  10. 10.
    Eckermann S, Coory M, Willan AR. Indirect comparison: relative risk fallacies and odds solution. J Clin Epidemiol 2009; 62: 1031–6PubMedCrossRefGoogle Scholar
  11. 11.
    Australian Government, Department of Health and Ageing. Guidelines for preparing submissions to the Pharmaceutical Benefits Advisory Committee (version 4.3) [online]. Available from URL: [Accessed 2010 Oct 25]Google Scholar
  12. 12.
    Greenland S, Robins J. Identifiability, exchangeability, and epidemiological confounding. Int J Epidemiol 1986; 15: 412–8CrossRefGoogle Scholar
  13. 13.
    Australian Government, Department of Health and Ageing. Public summary documents by product: natalizumab, concentrated solution for IV infusion, 300mg per 15mL,Tysabri® November 2006 [online]. Available from URL: [Accessed 2008 Oct 14]Google Scholar
  14. 14.
    Polman CH, O’Connor PW, Havrdove E, et al. A randomized, placebo-controlled trial of natalizumab for relapsing multiple sclerosis. N Engl J Med 2006; 354 (9): 899–910PubMedCrossRefGoogle Scholar
  15. 15.
    The IFNB Multiple Sclerosis Study Group and The University of British Columbia MS/MRI Analysis Group. Interferon beta-1b in the treatment of multiple sclerosis: final outcome of the randomized controlled trial. Neurology 1995; 45 (7): 1277–85CrossRefGoogle Scholar
  16. 16.
    Greenland S. Interpretation and choice of effect measures in epidemiologic analyses. Am J Epidemiol 1987; 125 (5): 761–8PubMedGoogle Scholar
  17. 17.
    Altman DG. Practical statistics for medical research. London: CRC Press, 1991: 611Google Scholar
  18. 18.
    Localio AR, Margolis DJ, Berlin JA. Relative risks and confidence intervals were easily computed indirectly from multivariable logistic regression. J Clin Epidemiol 2007; 60 (9): 874–82PubMedCrossRefGoogle Scholar
  19. 19.
    Eckermann S. Hospital performance including quality: creating economic incentives consistent with evidencebased medicine [dissertation]. Sydney (NSW): University of New South Wales, 2004 [online]. Available from URL: [Accessed 2010 Jul 1]Google Scholar
  20. 20.
    Eckermann S, Briggs A, Willan AR. Health technology assessment in the cost-disutility plane. Med Decis Making 2008; 28 (2): 172–81PubMedCrossRefGoogle Scholar
  21. 21.
    Eckermann S, Coelli T. Including quality attributes in a model of health care efficiency: a net benefit approach. Centre for Efficiency and Productivity Analysis Working Paper Series no. WP03/2008 [online]. Available from URL: [Accessed 2010 Oct 8]Google Scholar
  22. 22.
    Eckermann S. Measuring health system efficiency and funding for net benefit maximisation: the health economics of quality of care. Flinders Centre for Clinical Change and Health Care Research Working Paper no. 2009/08 [online]. Available from URL: [Accessed 2010 Oct 8]Google Scholar

Copyright information

© Springer International Publishing AG 2011

Authors and Affiliations

  • Simon Eckermann
    • 1
    Email author
  • Michael Coory
    • 2
  • Adrew R. Willan
    • 3
  1. 1.Centre for Health Services DevelopmentUniversity of WollongongWollongongAustralia
  2. 2.Cancer Epidemiology Centre, Cancer CouncilCarltonAustralia
  3. 3.SickKids Research Institute and University of TorontoTorontoCanada

Personalised recommendations