An exact confidence interval for a common effect size

  • Guido KnappEmail author


Approximative confidence intervals for a common standardized mean difference from a series of independent experiments are reasonably accurate when effect sizes are less than 1.5 in absolute magnitude and the sample sizes in each group are at least 10. In this article, we derive an exact confidence interval for this effect size where the bounds have to be determined by solving nonlinear equations. As a by-product, we obtain a median unbiased estimator of the common effect size.


Meta-analysis parameterized p value standardized difference of normal means homogeneity of effect sizes 

AMS Subject Classification



Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Hartung, J., and G. Knapp. 2001. On tests of the overall treatment effect in the meta-analysis with normally distributed responses. Statistics in Medicine 20:1771–82.CrossRefGoogle Scholar
  2. Hartung, J., and G. Knapp. 2011. Statistical inference in adaptive group sequential trials with the standardized mean difference as effect size. Sequential Analysis 30:94–113.MathSciNetCrossRefGoogle Scholar
  3. Hartung, J., G. Knapp, and B.K. Sinha. 2008. Statistical meta-analysis with applications. New York NY: Wiley.CrossRefGoogle Scholar
  4. Hedges, L. V. 1981. Distribution theory for Glass’s estimator of effect size and related estimators. Journal of Educational Statistics 6:107–28.CrossRefGoogle Scholar
  5. Hedges, L. V., and I. Olkin. 1985. Statistical methods for meta-analysis. Boston MA: Academic Press.zbMATHGoogle Scholar
  6. Hollands, G. J., I. Shemilt, T. M. Marteau, S. A. Jebb, H. B. Lewis, Y. Wei, J. P. T. Higgins, D. Ogilvie. 2015. Portion, package or tableware size for changing selection and consumption of food, alcohol and tobacco. Database of Systematic Reviews 14(9):CD011045. doi:10.1002/14651858. CD011045.pub2.Google Scholar
  7. R Development Core Team. 2016. R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. Scholar
  8. Singh, K., M. Xie, and W. E. Strawderman. 2005. Combining information from independent sources through confidence distributions. Annals of Statistics 33:159–83.MathSciNetCrossRefGoogle Scholar
  9. Veroniki, Α. Α., D. Jackson, W. Viechtbauer, R. Bender, J. Bowden, G. Knapp, O. Kuß, J.P.T. Higgins, D. Langan, and G. Salanti. 2016. Methods to estimate the between-study variance and its uncertainty in meta-analysis. Research Synthesis Methods 7:55–79.CrossRefGoogle Scholar
  10. Wiksten, Α., G. Rücker, and G. Schwarzer. 2016. Hartung-Knapp method is not always conservative compared with fixed-effect meta-analysis. Statistics in Medicine 35:2503–515.MathSciNetCrossRefGoogle Scholar

Copyright information

© Grace Scientific Publishing 2018

Authors and Affiliations

  1. 1.Department of StatisticsTU Dortmund UniversityDortmundGermany

Personalised recommendations