|
Activity Number:
|
345
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 8, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #306319 |
|
Title:
|
The Oklahoma Oral Health Needs Assessment: Comparison of Sampling Methods Using Monte Carlo Simulations
|
|
Author(s):
|
Emily Leary*+
|
|
Companies:
|
The University of Oklahoma Health Sciences Center
|
|
Address:
|
P.O. Box 5293, Norman, 73070,
|
|
Keywords:
|
simulation ; sample design ; multistage sampling
|
|
Abstract:
|
The objective of this study is to compare sampling, weighting, and variance estimation methods for the Oklahoma Oral Health Needs Assessment. The proportion of third grade children who have received protective dental sealants on at least one permanent molar tooth is the binary variable used to perform the simulations. The sealant population was built to simulate the proportion of third graders with dental sealants for each simulated sampled school. Weighted and unweighted estimates from a regionally stratified sample, a probability proportional to size sample, and a two-phase stratified method using counties are reported. Appropriate weighting methods were used for each sampling design as well as two variance estimation techniques: linearization and jackknifing. The distributions of all weighted and unweighted estimates are compared to population values.
|
