Stats
Growth curves (March 1, 2005).
Category: Nonlinear regression
The New York Times has a nice article about Dr. James Tanner, an expert on
childhood growth.
- With His Bells and Curves, Human Growth Science Grew Up. Hall SS.
The New York Times, March 1, 2005.
This article contrasts the growth charts developed by Dr. Tanner with
growth charts developed by the
U.S. Centers for Disease Control and Prevention.
Dr. Tanner and his colleagues at the Institute for Child Health in
London revolutionized growth charts in the 1960's by taking into account
variations in a child's tempo of growth. Rather than one-size-fits-all
curves, the Tanner-derived charts have separate curves, with a separate set
of percentiles, for early-, average- and late-maturing boys and girls. Thus
they expand the range of normal growth, using curves that are more
forgiving of individual variation, especially around the crucial time of
puberty.
These subtle differences derive from the kind of data used to create a
growth chart. The American charts (and some modern European charts)
primarily rely on cross-sectional data: researchers take a large group of
children, separate them by age, measure them one time and then plot the
distribution of heights and weights for each age group.
In contrast, Dr. Tanner and others believe a more accurate (and
flexible) picture of a child's growth emerges from so-called longitudinal
studies, where the same children are repeatedly measured over the course of
many years of growth, so that individual variations in tempo - those who
mature early and those who mature late - can be statistically incorporated
into the charts. The data for such charts are more logistically difficult
and costly to collect. But some growth experts believe such charts provide
a more realistic picture of variation in individual growth patterns.
Even though the CDC approach may be simplistic, it is still relies on a
very sophisticated model that allows for changes over time in the spread of
the data and in the skewness of the data.
07/08/2008.