Activity Number:
|
292
- Small Area Estimation with Small Samples
|
Type:
|
Topic Contributed
|
Date/Time:
|
Tuesday, July 31, 2018 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Survey Research Methods Section
|
Abstract #328375
|
Presentation
|
Title:
|
Spatial-Temporal Small Area Estimation Models for Cancer Incidence
|
Author(s):
|
Benmei Liu* and Li Zhu and Huann-Sheng Chen and Joe Zou and Rebecca Siegel and Kim D. Miller and Ahmedin Jemal and Eric J. Feuer
|
Companies:
|
National Cancer Institute and National Cancer Institute and National Cancer Institute and Information Management Services and American Cancer Society and American Cancer Society and American Cancer Society and National Cancer Institute
|
Keywords:
|
cancer incidence;
missing data;
small samples;
spatial-temporal modeling;
disease mapping
|
Abstract:
|
The number of cancer diagnosed in the current calendar year in the United States overall and in each state is not known because the most recent year for which incidence data is available lags four years behind because of the time required for data collection, compilation and dissemination. In addition, high-quality incidence data have not been achieved in all states historically due to data quality concerns and different releasing roles across different cancer registries, and the total number of cases in the most recent 1 to 3 data years are incomplete because of delays in reporting. Furthermore, previous studies have focused on reporting geographic variation in cancer incidence by state and less information are available at the county level. Many of the counties have sparse data due to small or zero sample sizes especially for less common cancer sites. This paper summaries our research on applying spatial-temporal small area estimation models to predict the historically missing data at the state level and to predict or smooth the county-level estimates. Validation of our modeled estimates will be also demonstrated.
|
Authors who are presenting talks have a * after their name.