Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2002:2:1.
doi: 10.1186/1471-2288-2-1. Epub 2002 Jan 25.

Simpson's paradox and calculation of number needed to treat from meta-analysis

Christopher J Cates  1
Affiliations

Simpson's paradox and calculation of number needed to treat from meta-analysis

Christopher J Cates. BMC Med Res Methodol. 2002.

Abstract

Background: Calculation of numbers needed to treat (NNT) is more complex from meta-analysis than from single trials. Treating the data as if it all came from one trial may lead to misleading results when the trial arms are imbalanced.

Discussion: An example is shown from a published Cochrane review in which the benefit of nursing intervention for smoking cessation is shown by formal meta-analysis of the individual trial results. However if these patients were added together as if they all came from one trial the direction of the effect appears to be reversed (due to Simpson's paradox). Whilst NNT from meta-analysis can be calculated from pooled Risk Differences, this is unlikely to be a stable method unless the event rates in the control groups are very similar. Since in practice event rates vary considerably, the use a relative measure, such as Odds Ratio or Relative Risk is advocated. These can be applied to different levels of baseline risk to generate a risk specific NNT for the treatment.

Summary: The method used to calculate NNT from meta-analysis should be clearly stated, and adding the patients from separate trials as if they all came from one trial should be avoided.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Risk Difference meta-analysis of trials of high intensity nursing intervention for smoking cessation (showing proportion of patients in each trial arm who had ceased smoking at the longest follow-up). The trial results are combined using the Mantel-Haenszel fixed effects method.
Figure 2
Figure 2
Risk Difference meta-analysis of trials of high intensity nursing intervention for smoking cessation (showing proportion of patients in each trial arm who had ceased smoking at the longest follow-up). The meta-analysis is performed using a random effects model and the confidence interval of the pooled result is wider than for the fixed effects method.
Figure 3
Figure 3
Odds Ratio meta-analysis of trials of high intensity nursing intervention for smoking cessation (showing proportion of patients in each trial arm who had ceased smoking at the longest follow-up). The trial results are combined using the Mantel-Haenszel fixed effects method.
See this image and copyright information in PMC

Comment in

References

    1. Miller NH, Smith PM, DeBusk RF, Sobel DS, Taylor CB. Smoking cessation in hospitalized patients – Results of a randomized trial. Arch Intern Med. 1997;157:409–15. doi: 10.1001/archinte.157.4.409. - DOI - PubMed
    1. Rice VH, Stead LF. The Cochrane Library, Oxford: Update Software.; 2001. Nursing interventions for smoking cessation (Cochrane Review). - PubMed
    1. Number Needed to Treat (NNT) Bandolier. 1999;59:i–iv. http://www.jr2.ox.ac.uk/bandolier/band59/NNT1.html - PubMed
    1. Blyth C. On Simpson's paradox and the sure-thing principle. J Am Statistical Assn. 1972;67:364–366.
    1. Altman DG. Confidence intervals for the number needed to treat. BMJ. 1998;317:1309–1312. - PMC - PubMed

MeSH terms