Related Experiment Videos
Comparison of two cluster sampling methods for health surveys in developing countries
Paul Milligan1, Alpha Njie, Steve Bennett
1MRC Laboratories, The Gambia. pmilligan@mrc.gm
International Journal of Epidemiology
|March 17, 2004
Summary
The Expanded Program for Immunization (EPI) random walk method provides accurate vaccination coverage estimates but lacks objectivity. Compact segment sampling is preferred for its objectivity and ability to estimate population totals for better service planning.
Area of Science:
- Public Health
- Epidemiology
- Survey Methodology
Background:
- The Expanded Program for Immunization (EPI) random walk method is a common, rapid survey technique when household frames are unavailable.
- However, EPI is not a probability sample, doesn't account for population changes, and lacks objective household selection and non-response callbacks.
- Compact segment sampling offers a more rigorous alternative, addressing these limitations.
Purpose of the Study:
- To compare the EPI random walk method with compact segment sampling for estimating vaccination coverage.
- To evaluate the impact of population movement on survey accuracy.
Main Methods:
- Two surveys were conducted in The Gambia within three months: one using the EPI scheme and one using compact segment sampling.
- Both surveys aimed to estimate vaccination coverage in the Western Region.
Main Results:
- Vaccination coverage point estimates from both methods rarely differed by more than 2%.
- Observed differences were more attributable to household selection than population movement.
- A mathematical model indicated that ignoring population movement has minimal impact on results.
Conclusions:
- The EPI random walk method can yield accurate and precise vaccination coverage data if fieldwork quality is high.
- Compact segment sampling is generally superior due to objective household selection and the ability to estimate population totals for service planning.