JSM 2004 - Toronto

Abstract #301749

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2004 Program page
Activity Number: 152
Type: Topic Contributed
Date/Time: Monday, August 9, 2004 : 2:00 PM to 3:50 PM
Sponsor: Section on Government Statistics
Abstract - #301749
Title: Subgroup Effects in Analysis of Pubertal Landmarks and Body Habitus
Author(s): Melinda L. Drum*+ and Robert L. Rosenfield and Rebecca B. Lipton
Companies: University of Chicago and University of Chicago and University of Chicago
Address: 5841 S. Maryland Ave., MC 2007, Chicago, IL, 60637-1470,
Keywords: factorial models ; interactions ; NHANES-III
Abstract:

Complex interactions in factorial regression may result from atypical subgroups that contribute little information to the question of interest. We encountered this situation when using NHANES III data to model attainment of pubertal landmarks on age-sex specific BMI percentile and waist circumference in 3,197 (1,609 girls, 1,588 boys) nonhispanic black, nonhispanic white, and Mexican American youth ages 8-15, using logistic regression with NHANES survey sampling strata and probability weights. Multiple interactions involving age, race-ethnicity and body habitus were traced to two classes of atypical subgroups. Effectively all 14-15 year olds (95-100% over subgroups) had passed all the pubertal landmarks and other age groups had uniformly passed selected landmarks, providing little information. Among the leanest 2.5% (35 boys, 44 girls with BMI<5th percentile), low attainment of the pubertal landmarks was of interest, but the small numbers led to many zero cell counts, aliasing and inability to estimate contrasts of interest. When such subgroups were excluded, at most a single two-way interaction, clearly interpretable and clinically meaningful, remained for each pubertal landmark.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2004 program

JSM 2004 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2004