ROC curve and covariates: extending induced methodology to the non-parametric framework
Continuous diagnostic tests are often used to discriminate between diseased and healthy populations. The receiver operating characteristic (ROC) curve is a widely used tool that provides a graphical visualisation of the effectiveness of such tests. The potential performance of the tests in terms of distinguishing diseased from healthy people may be strongly influenced by covariates, and a variety of regression methods for adjusting ROC curves has been developed. Until now, these methodologies have assumed that covariate effects have parametric forms, but in this paper we extend the induced methodology by allowing for arbitrary non-parametric effects of a continuous covariate. To this end, local polynomial kernel smoothers are used in the estimation procedure. Our method allows for covariate effect not only on the mean, but also on the variance of the diagnostic test. We also present a bootstrap-based method for testing for a significant covariate effect on the ROC curve. To illustrate the method, endocrine data were analysed with the aim of assessing the performance of anthropometry for predicting clusters of cardiovascular risk factors in an adult population in Galicia (NW Spain), duly adjusted for age. The proposed methodology has proved useful for providing age-specific thresholds for anthropometric measures in the Galician community.
KeywordsROC curve Non-parametric regression Bootstrap Cardiovascular risk factors Anthropometric measures
Unable to display preview. Download preview PDF.
- Carey, V.J., Walters, E.E., Colditz, G.A., Solomon, C.G., Willet, W.C., Rosner, B.A., Speizer, F.E., Manson, J.E.: Body fat distribution and risk of noninsulin-dependent diabetes in women: the Nurses’ Health Study. Am. J. Epidemiol. 145, 614–619 (1997) Google Scholar
- Chumlea, W.C., Baumgartner, R.N., Garry, P.J., Rhyne, R.L., Nicholson, C., Wayne, S.: Fat distribution and blood lipids in a sample of healthy elderly people. Int. J. Obes. 16, 125–133 (1992) Google Scholar
- Fan, J., Gijbels, I.: Local Polynomial Modelling and Its Applications. Chapman & Hall, CRC (1996) Google Scholar
- Hu, G., Qiao, Q., Tuomilehto, J., Eliasson, M., Feskens, E.J., Pyörälä, K.: Plasma insulin and cardiovascular mortality in non-diabetic European men and women: a meta-analysis of data from eleven prospective studies. The DECODE Insulin Study Group. Diabetologia 47, 1245–1256 (2004) Google Scholar
- International Diabetes Federation: The IDF consensus worldwide definition of the metabolic syndrome. http://www.idf.org/webdata/docs/IDF_Meta_def_final.pdf (2008). Accessed 7 September 2009
- Peden, M., McGee, K., Krug, E. (eds.): Injury: A Leading Cause of the Global Burden of Disease, 2000. World Health Organization, Geneva (2006) Google Scholar
- Swets, J.A., Pickett, R.M.: Evaluation of Diagnostic Systems: Methods from Signal Detection Theory. Academic Press, New York (1982) Google Scholar
- Tomé, M.A., Botana, M.A., Cadarso-Suárez, C., Rego-Iraeta, A., Fernández-Mariño, A., Mato, J.A., Solache, I., Perez-Fernandez, R.: Prevalence of metabolic syndrome in Galicia (NW Spain) on four alternative definitions and association with insulin resistance. J. Endocrinol. Invest. 32, 505–511 (2008) Google Scholar