Display options
Cite
Setodji CM, Scheuner M, Pankow JS, et al. A graphical method for assessing risk factor threshold values using the generalized additive model: the multi-ethnic study of atherosclerosis. Health Serv Outcomes Res Methodol. 2012;12(1):62-79doi: 10.1007/s10742-012-0082-1.
Setodji, C. M., Scheuner, M., Pankow, J. S., Blumenthal, R. S., Chen, H., & Keeler, E. (2012). A graphical method for assessing risk factor threshold values using the generalized additive model: the multi-ethnic study of atherosclerosis. Health services & outcomes research methodology, 12(1), 62-79. https://doi.org/10.1007/s10742-012-0082-1
Setodji, Claude Messan, et al. "A graphical method for assessing risk factor threshold values using the generalized additive model: the multi-ethnic study of atherosclerosis." Health services & outcomes research methodology vol. 12,1 (2012): 62-79. doi: https://doi.org/10.1007/s10742-012-0082-1
Setodji CM, Scheuner M, Pankow JS, Blumenthal RS, Chen H, Keeler E. A graphical method for assessing risk factor threshold values using the generalized additive model: the multi-ethnic study of atherosclerosis. Health Serv Outcomes Res Methodol. 2012 Mar;12(1):62-79. doi: 10.1007/s10742-012-0082-1. PMID: 22593642; PMCID: PMC3351005.
Copy Download .nbib Format: NLM
Share it on

Health Serv Outcomes Res Methodol. 2012 Mar;12(1):62-79. doi: 10.1007/s10742-012-0082-1.

A graphical method for assessing risk factor threshold values using the generalized additive model: the multi-ethnic study of atherosclerosis.

Health services & outcomes research methodology

Claude Messan Setodji, Maren Scheuner, James S Pankow, Roger S Blumenthal, Haiying Chen, Emmett Keeler

Affiliations

  1. RAND, Pittsburgh, PA 15213, USA [email protected].

PMID: 22593642 PMCID: PMC3351005 DOI: 10.1007/s10742-012-0082-1

Abstract

Continuous variable dichotomization is a popular technique used in the estimation of the effect of risk factors on health outcomes in multivariate regression settings. Researchers follow this practice in order to simplify data analysis, which it unquestionably does. However thresholds used to dichotomize those variables are usually ad-hoc, based on expert opinions, or mean, median or quantile splits and can add bias to the effect of the risk factors on specific outcomes and underestimate such effect. In this paper, we suggest the use of a semi-parametric method and visualization for improvement of the threshold selection in variable dichotomization while accounting for mixture distributions in the outcome of interest and adjusting for covariates. For clinicians, these empirically based thresholds of risk factors, if they exist, could be informative in terms of the highest or lowest point of a risk factor beyond which no additional impact on the outcome should be expected.

References

  1. N Engl J Med. 2008 Mar 27;358(13):1336-45 - PubMed
  2. Circulation. 2007 Aug 7;116(6):619-26 - PubMed
  3. Stat Med. 2004 Apr 15;23(7):1159-78 - PubMed
  4. Pediatrics. 2004 May;113(5):1352-6 - PubMed
  5. J Natl Cancer Inst. 1994 Jun 1;86(11):829-35 - PubMed
  6. Obstet Gynecol. 1997 Mar;89(3):351-4 - PubMed
  7. Am J Epidemiol. 2002 Nov 1;156(9):871-81 - PubMed
  8. J Am Coll Cardiol. 1985 Jun;5(6 Suppl):141B-149B - PubMed
  9. J Health Econ. 1998 Jun;17(3):247-81 - PubMed
  10. JAMA. 2001 May 16;285(19):2486-97 - PubMed
  11. Circulation. 2008 Feb 12;117(6):743-53 - PubMed
  12. Arch Intern Med. 2004 Jun 28;164(12):1285-92 - PubMed
  13. Biometrics. 2004 Jun;60(2):504-9 - PubMed
  14. Stat Med. 2006 Jan 15;25(1):127-41 - PubMed
  15. Biometrics. 1999 Jun;55(2):652-9 - PubMed
  16. Genet Med. 2008 Dec;10(12):879-87 - PubMed

Publication Types

Grant support