Journal of Clinical Epidemiology
Volume 63, Issue 11 , Pages 1223-1231 , November 2010

Logistic regression was preferred to estimate risk differences and numbers needed to be exposed adjusted for covariates

  • Ulrich Gehrmann

      Affiliations

    • Department of Medical Biometry, Institute for Quality and Efficiency in Health Care (IQWiG), Cologne, Germany
    • ,
  • Oliver Kuss

      Affiliations

    • Institute for Medical Epidemiology, Biostatistics, and Informatics (IMEBI), Martin-Luther-University Halle-Wittenberg, Halle (Saale), Germany
    • ,
  • Jürgen Wellmann

      Affiliations

    • Institute of Epidemiology and Social Medicine, University of Münster, Münster, Germany
    • ,
  • Ralf Bender

      Affiliations

    • Department of Medical Biometry, Institute for Quality and Efficiency in Health Care (IQWiG), Cologne, Germany
    • Faculty of Medicine, University of Cologne, Cologne, Germany
    • Corresponding Author InformationCorresponding author. Department of Medical Biometry, Institute for Quality and Efficiency in Health Care (IQWiG), Dillenburger Street 27, D-51105 Cologne, Germany. Tel.: +49-221-35685-451; fax: +49-221-35685-891.

,Accepted 22 January 2010.

References 

  1. Heller RF, Dobson AJ, Attia J, Page J. Impact numbers: measures of risk factor impact on the whole population from case-control and cohort studies. J Epidemiol Community Health. 2002;56:606–610
  2. Bender R. Number needed to treat (NNT). In:  Armitage P,  Colton T editor. Encyclopedia of biostatistics. 2nd ed. Chichester, UK: Wiley; 2005;p. 3752–3761
  3. Bender R, Blettner M. Calculating the “number needed to be exposed” with adjustment for confounding variables in epidemiological studies. J Clin Epidemiol. 2002;55:525–530
  4. Bender R, Kuss O, Hildebrandt M, Gehrmann U. Estimating adjusted NNT measures in logistic regression analysis. Stat Med. 2007;26:5586–5595
  5. Cheung YB. A modified least-squares regression approach to the estimation of risk difference. Am J Epidemiol. 2007;166:1337–1344
  6. Spiegelman D, Hertzmark E. Easy SAS calculations for risk or prevalence ratios and differences. Am J Epidemiol. 2005;162:199–200
  7. Wacholder S. Binomial regression in GLIM: estimating risk ratios and risk differences. Am J Epidemiol. 1986;123:174–184
  8. Agresti A. Categorical data analysis. 2nd ed. New York, NY: Wiley; 2002;
  9. Wellmann J, Taeger D, Behrens T, Kim R, Maurer H. [Relative risks in a log-linear model under constraints by using the SAS procedure NLP]. In:  Rödel E,  Bödeker R-H editor. SAS®: Verbindung von Theorie mit Praxis - Proceedings der 9. Konferenz der SAS®-Anwender in Forschung und Entwicklung (KSFE) [SAS®: Connection of Theory and Praxis - Proceedings of the 9th Conference of SAS® Users in Research and Development (KSFE)]. Aachen, Germany: Shaker; 2005;p. 381–390
  10. Altman DG. Confidence intervals for the number needed to treat. BMJ. 1998;317:1309–1312
  11. Bender R. Calculating confidence intervals for the number needed to treat. Control Clin Trials. 2001;22:102–110
  12. Myers RH, Montgomery DC, Vining GG. Generalized linear models: with applications in engineering and the sciences. New York, NY: Wiley; 2002;
  13. Bender R, Hildebrandt M, Kuss O. [Calculation of adjusted NNEs in cohort studies]. In:  Kaiser K,  Bödeker R-H editor. Statistik und Datenanalyse mit SAS® - Proceedings der 10. Konferenz der SAS®-Anwender in Forschung und Entwicklung (KSFE) [Statistics and Data Analysis with SAS® - Proceedings of the 10th Conference of SAS® Users in Research and Development (KSFE)]. Aachen, Germany: Shaker; 2006;p. 19–33
  14. Kleinbaum DG, Klein M. Logistic regression: a self-learning text. New York, NY: Springer; 2002;
  15. Royston P, Ambler G, Sauerbrei W. The use of fractional polynomials to model continuous risk variables in epidemiology. Int J Epidemiol. 1999;28:964–974
  16. Hosmer DW, Lemeshow S. Applied logistic regression. 2nd ed. New York, NY: Wiley; 2000;
  17. Localio AR, Margolis DJ, Berlin JA. Relative risks and confidence intervals were easily computed indirectly from multivariable logistic regression. J Clin Epidemiol. 2007;60:874–882
  18. Bender R, Kuss O. Methods to calculate relative risks, risk differences, and numbers needed to treat from logistic regression. J Clin Epidemiol. 2010;63:7–8
  19. Stang A, Poole C, Bender R. Common problems related to the use of number needed to treat. J Clin Epidemiol. 2010;63:820–825

PII: S0895-4356(10)00045-4

doi: 10.1016/j.jclinepi.2010.01.011

Journal of Clinical Epidemiology
Volume 63, Issue 11 , Pages 1223-1231 , November 2010

Article Tools