Statistical Methods and Applications

, Volume 11, Issue 1, pp 127–138 | Cite as

On pooling data summaries in the absence of interactions “response-by-study”

  • Kepher Henry Makambi
Statistical Applications

Abstract

The standard hypothesis testing procedure in meta-analysis (or multi-center clinical trials) in the absence of treatment-by-center interaction relies on approximating the null distribution of the standard test statistic by a standard normal distribution. For relatively small sample sizes, the standard procedure has been shown by various authors to have poor control of the type I error probability, leading to too many liberal decisions. In this article, two test procedures are proposed, which rely on thet—distribution as the reference distribution. A simulation study indicates that the proposed procedures attain significance levels closer to the nominal level compared with the standard procedure.

Key words

Fixed effects model Patnaik's approximation attained significance levels confidence intervals probability difference 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Boeckenhoff A, Hartung J (1998) Some corrections of the significance level in meta-analysis.Biometrical Journal 40: 937–947MATHCrossRefGoogle Scholar
  2. Brockwell SE, Gordon IR (2001) A comparison of statistical methods for meta-analysis.Statistics in Medicine 20: 825–840CrossRefGoogle Scholar
  3. Canner PL (1987) An overview of six clinical trials of aspirin in the coronary heart disease.Statistics in Medicine 6: 255–263Google Scholar
  4. Cochran WG (1954) The combination of estimates from different experiments.Biometrics 10: 101–129MathSciNetCrossRefGoogle Scholar
  5. De Beucklaer A (1997) A closer examination on some parametric alternatives to the ANOVA F-test.Statistical Papers 37: 291–305CrossRefGoogle Scholar
  6. DerSimonian R, Laird NM (1986) Meta-analysis in clinical trials.Controlled Clinical Trials 7: 177–188.CrossRefGoogle Scholar
  7. Feigin PD, Lumelskii YP (2000) On the confidence limits for the difference of two binomial parameters.Communications in Statistics-Theory and Methods 29: 131–141MATHMathSciNetGoogle Scholar
  8. Follman DA, Proschan MA (1999) Valid inference in random effects meta-analysis.Biometrics 55: 732–737CrossRefGoogle Scholar
  9. Hardy RJ, Thompson SG (1996) A likelihood approach to meta-analysis with random effects.Statistics in Medicine 15: 619–629CrossRefGoogle Scholar
  10. Hartung J (1976) Some inequalities for a random function.Teorija Verojatnostei i ee Primenenja 21: 661–665 (also in: Theory of Probability and its applications, SIAM 21, 1977)MATHMathSciNetGoogle Scholar
  11. Hartung J (1999) An alternative method for meta-analysis.Biometrical Journal 41: 901–916MATHMathSciNetCrossRefGoogle Scholar
  12. Hartung J, Voet B (1986) Best invariant unbiased estimators for the mean squared error of variance component estimators.Journal of the American Statistical Association 81: 689–691MATHMathSciNetCrossRefGoogle Scholar
  13. Hedges L, Olkin I (1985) Statistical methods for meta-analysis. Orlando, FL: Academic PressMATHGoogle Scholar
  14. Li Y, Shi L, Roth HD (1994) The bias of the commonly used estimate of variance in meta-analysis.Communications in Statistics—Theory and Methods 23: 1063–1085MATHMathSciNetGoogle Scholar
  15. Makambi KH, Argac D, Hartung J (2000) On the meta-analysis of treatment differences in heteroscedastic samples.Biometrical Letters (Listy Biometryczne) 37: 1–11MATHGoogle Scholar
  16. Meier P (1953) Variance of a weighted mean.Biometrics 9, 59–73MathSciNetCrossRefGoogle Scholar
  17. Normand S-L (1999) Meta-analysis: formulating, evaluating, combining, and reporting.Statistics in Medicine 18: 321–359CrossRefGoogle Scholar
  18. Patnaik PB (1949) The non-central χ2- and F-distributions and their applications.Biometrika 36: 202–232MATHMathSciNetCrossRefGoogle Scholar
  19. Schmid JE, Koch GG, LaVange LM (1991) An overview of statistical issues and methods of meta-analysis.Journal of Biopharmaceutical Statistics 1, 103–120Google Scholar
  20. Tiwari HK, Elston RC (1999) The approximate variance of a function of random variables.Biometrical Journal 41, 351–357MATHMathSciNetCrossRefGoogle Scholar
  21. Weiler H, Culpin D (1970) On the variance of weighted means.Technometrics 12, 757–773MATHCrossRefGoogle Scholar
  22. Whitehead A, Whitehead J (1991) A general parametric approach to meta-analysis of randomised clinical trials.Statistics in Medicine 10: 1665–1677Google Scholar

Copyright information

© Springer-Verlag 2002

Authors and Affiliations

  • Kepher Henry Makambi
    • 1
  1. 1.Howard University Cancer CenterWashington, D.C.USA

Personalised recommendations