sitar-package: SITAR (SuperImposition by Translation And Rotation) growth curve analysis

Description

SITAR is a method of growth curve analysis, based on nlme, that estimates a single mean growth curve as a regression spline, plus a set of up to three fixed and random effects (a, b and c) defining how individual growth curves differ from the mean curve. SITAR stands for SuperImposition by Translation And Rotation. The package also contains some utility functions for the LMS method, as used to construct growth reference centiles (see gamlss).

Arguments

Details

ll{ Package: sitar Type: Package Version: 1.0 Date: 2013-09-23 License: GPL-2 } Effect a (or alpha) measures size, and is a random intercept relative to the spline curve intercept. Effect b (or beta) measures tempo, the timing of the growth process, and reflects a shift on the x scale relative to the mean. Effect c (or gamma) is velocity, and indicates how the x scale is stretched or shrunk reflecting the rate at which 'time' passes for individuals. The aim is for individual curves, adjusted for a, b and c, to lie on top of the mean curve. The package creates an object of class sitar, based on nlme, representing the nonlinear mixed-effects model fit. Generic functions such as print, plot and summary have methods to show the results of the fit. The functions resid, coef, fitted, fixed.effects, and random.effects can be used to extract some of its components. The functions devadj and varexp compare respectively the deviance and variance explained of a series of models, taking into account any transformations of the y variable. Functions plotclean, velout, codeplot and zapvelout are useful to clean the data file.

References

The idea of SITAR growth curve analysis arose from the paper by Beath (2007) and was first described in Cole et al (2010). The other references describe applications of SITAR to a variety of data forms.

Beath KJ. Infant growth modelling using a shape invariant model with random efffects. Stat Med 2007;26:2547-64.

Cole TJ, Cortina Borja M, Sandhu J, et al. Nonlinear growth generates age changes in the moments of the frequency distribution: the example of height in puberty. Biostatistics 2008;9:159-71.

Cole TJ, Donaldson MD, Ben-Shlomo Y. SITAR--a useful instrument for growth curve analysis. Int J Epidemiol 2010;39:1558-66.

Gault EJ, Perry RJ, Cole TJ, et al. Effect of oxandrolone and timing of pubertal induction on final height in Turner's syndrome: randomised, double blind, placebo controlled trial. BMJ 2011;342:d1980.

Johnson L, Llewellyn CH, van Jaarsveld CHM, et al. Genetic and environmental influences on infant growth: prospective analysis of the Gemini twin birth cohort. PLoS ONE 2011;6:e19918.

Prentice A, Dibba B, Sawo Y, et al. The effect of prepubertal calcium carbonate supplementation on the age of peak height velocity in Gambian adolescents. Am J Clin Nutr 2012;96:1042-50.

Dean MC, Cole TJ. Human life history evolution explains dissociation between the timing of tooth eruption and peak rates of root growth. PLoS ONE 2013;8:e54534.