Quantile regression methods for reference growth charts
Article first published online: 5 SEP 2005
Copyright © 2005 John Wiley & Sons, Ltd.
Statistics in Medicine
Volume 25, Issue 8, pages 1369–1382, 30 April 2006
How to Cite
Wei, Y., Pere, A., Koenker, R. and He, X. (2006), Quantile regression methods for reference growth charts. Statist. Med., 25: 1369–1382. doi: 10.1002/sim.2271
- Issue published online: 22 MAR 2006
- Article first published online: 5 SEP 2005
- Manuscript Accepted: APR 2005
- Manuscript Received: AUG 2004
- NSF. Grant Numbers: DMS-01-02411, SES-02-40781
- quantile regression;
- growth curves;
- longitudinal data
Estimation of reference growth curves for children's height and weight has traditionally relied on normal theory to construct families of quantile curves based on samples from the reference population. Age-specific parametric transformation has been used to significantly broaden the applicability of these normal theory methods. Non-parametric quantile regression methods offer a complementary strategy for estimating conditional quantile functions. We compare estimated reference curves for height using the penalized likelihood approach of Cole and Green (Statistics in Medicine 1992; 11:1305–1319) with quantile regression curves based on data used for modern Finnish reference charts. An advantage of the quantile regression approach is that it is relatively easy to incorporate prior growth and other covariates into the analysis of longitudinal growth data. Quantile specific autoregressive models for unequally spaced measurements are introduced and their application to diagnostic screening is illustrated. Copyright © 2005 John Wiley & Sons, Ltd.