Activity Number:
|
361
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 14, 2002 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Survey Research Methods*
|
Abstract - #301430 |
Title:
|
Design and Clustering Effects in School Surveys
|
Author(s):
|
William Robb*+ and Ronaldo Iachan
|
Affiliation(s):
|
ORC Macro and ORC Macro
|
Address:
|
, , , ,
|
Keywords:
|
Design effects ; Generalized variance functions ; Clustering effects ; School surveys ; Weighting effects
|
Abstract:
|
This paper analyzes data from the Youth Risk Behavior Survey (YRBS) to assess the effects of clustering and unequal weighting for several population domains and key health risk factors. The YRBS uses a multi-stage stratified sampling design where first-stage units are county groupings and second-stage units are schools; probabilities proportional to size (PPS) sampling methods are used at these two stages. The analysis separates out clustering effects by estimating intra-cluster correlations. A parallel assessment of unequal weighting is based on the variability of weights computed at various stages and overall. General variance functions (GVF) methods are used to assess how these components vary across key domains and risk factors. This evaluation will help improve the understanding of sampling errors for school survey estimates and the design of such surveys generally.
|
- 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 2002 program |