|
Activity Number:
|
290
- Advanced Bayesian Topics (Part 3)
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 11, 2021 : 1:30 PM to 3:20 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
|
Abstract #318734
|
|
|
Title:
|
State-Level Estimation by Combining Information from Two Health Surveys
|
|
Author(s):
|
Diba Khan* and John R Pleis and Bill Cai and Benmei Liu and Eric J. Feuer and Van Parsons and Yulei He and Machell Town
|
|
Companies:
|
National Center for Health Statistics, Centers for Disease Control and Prevention and National Center for Health Statistics, Centers for Disease Control and Prevention and NCHS and National Cancer Institute and National Cancer Institute and CDC and US Centers for Disease Control and Prevention and Centers for Disease Control and Prevention
|
|
Keywords:
|
Bayesian;
survey;
estimation;
bias
|
|
Abstract:
|
Large national health surveys, such as the National Health Interview Survey (NHIS) and the Behavioral Risk Factors Surveillance Survey (BRFSS) collect data on cancer screening behaviors and certain risk factors such as smoking. The BRFSS is designed to provide state and sub-state direct estimates, such as for metropolitan and micropolitan statistical areas and has a large sample size. The NHIS is designed to provide national, regional, and selected state-specific direct estimates and has relatively higher response rates. Model-based small area estimates (SAEs) that combine information from multiple surveys have been used to adjust for possible non-response and coverage biases from BRFSS, a national health survey administered by telephone (landline/wireless). This study will examine the state-level distributions of these model-based adjustments for different outcomes by combining information from the BRFSS and NHIS. The suggested approach will be demonstrated using the 2011-16 BRFSS and NHIS.
|
Authors who are presenting talks have a * after their name.
