|
Activity Number:
|
4
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, August 6, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #304965 |
|
Title:
|
Development of Methodology for Production of Rapidly Available, County-Level, Small-Area Estimates To Monitor the Course of Influenza Vaccine Coverage
|
|
Author(s):
|
Haomiao Jia*+ and Michael W. Link and Ali H. Mokdad and James Holt and Lei Li and Paul S. Levy
|
|
Companies:
|
Mercer University School of Medicine and Centers for Disease Control and Prevention and Centers for Disease Control and Prevention and Centers for Disease Control and Prevention and RTI International and RTI International
|
|
Address:
|
1550 College Street, Macon, GA, 31207,
|
|
Keywords:
|
small area estimation ; GIS ; GLMM ; data smooth
|
|
Abstract:
|
This paper summarizes the methodology for the rapid production of county-level, small-area estimates (SAEs) of influenza vaccine coverage from the ongoing Behavior Risk Factor Surveillance System (BRFSS). Our objectives are construction of monthly vaccination rates that could be updated steadily and investigation of the differences between counties during the 2004--05 influenza season. We developed a procedure that utilizes random effects logistic regression followed by "head-banging" (a form of spatial smoothing). This method is suitable for situations such as this, where most of the counties have few respondents or none at all and there is a need for estimates to be generated quickly for purposes of surveillance. It also is adaptable to spatial-temporal mapping using the GIS system, which can provide visual scanning for clusters of hotspots having low vaccination coverage.
|
