Statistical Design, Sampling Weights, and Weight Adjustments of the School Physical Activity and Nutrition (SPAN) Population-Based Surveillance 2009--2010 Study

• Activity Number: 595
• Type: Contributed
• Date/Time: Wednesday, August 4, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Adriana Perez*+ and Deanna M. Hoelscher and Ralph F. Frankowski and R. Sue Day and Eun Sul Lee
• Companies: The University of Texas School of Public Health and Michael & Susan Dell Center for Advancement of Healthy Living and The University of Texas School of Public Health and The University of Texas School of Public Health and Oregon Health & Science University
• Keywords: complex survey ; missing data ; sampling frame ; sample size

Abstract

SPAN was designed to measure body mass index and related dietary and physical activity habits, knowledge, and attitudes in Texas school-aged children in grades 4, 8 and 11. The purpose of the study is to yield representative data at the Texas state level, to provide representative estimates for the Texas Department of State Health Services (TDSHS) health service regions, and to provide representative estimates comparing border and non-border counties in Texas. A complex survey design was implemented incorporating a multi-stage probability sample at the state level as well as by three major racial/ethnic groups: African American, Hispanic and White/Other. This paper provides an overview of the design and methods, sampling weights, and post-adjustment considerations of this school-based survey for the academic year 2009-2010 and describes the unique challenges of this project.