Related Experiment Videos
Capture-recapture methods to size alcohol related problems in a population
G Corrao1, V Bagnardi, G Vittadini
1Department of Statistics, Faculty of Statistical Sciences, Chair of Medical Statistics and Epidemiology, University of Milan, Bicocca, Italy. giovanni.corrao@unimib.it
Journal of Epidemiology and Community Health
|July 13, 2000
Summary
Capture-recapture methods effectively estimate alcohol-related disorder prevalence using multiple data sources. Adjustments for data source dependencies and heterogeneity improve accuracy for public health planning.
Area of Science:
- Epidemiology
- Biostatistics
- Public Health
Background:
- Estimating the prevalence of alcohol-related disorders is crucial for public health interventions.
- Multiple incomplete data sources often exist for identifying individuals with these disorders.
Purpose of the Study:
- To evaluate the utility of capture-recapture methods for estimating alcohol-related disorder prevalence.
- To assess the impact of dependencies and heterogeneity on these estimates.
Main Methods:
- A cross-sectional study was conducted in a large community.
- Four independent sources (self-help groups, psychiatric ambulatory care, public alcohology services, hospital discharges) identified cases.
- Log-linear models were used to adjust for source dependencies and age-related heterogeneity.
Main Results:
- Initial two-sample capture-recapture estimates were biased due to source dependencies.
- Log-linear model estimates, adjusted for dependencies, ranged from 2297 to 2523.
- Further adjustments for age-related heterogeneity refined prevalence estimates.
Conclusions:
- Capture-recapture methods are suitable for estimating prevalence of alcohol-related problems when diverse agency data are available.
- Accurate case definition and analysis of heterogeneity are critical for reliable estimates.
- Precise prevalence data are essential for effective public health planning and intervention evaluation.