Sampling in Health Geography: A Study in Vientiane
Author Information
Author(s): Julie Vallée, Marc Souris, Florence Fournet, Audrey Bochaton, Virginie Mobillion, Karine Peyronnie, Gérard Salem
Primary Institution: Institut de Recherche pour le Développement (IRD)
Hypothesis
How can geographical objectives and probabilistic methods be reconciled in health surveys?
Conclusion
Choosing clusters based on reasoned hypotheses can improve the statistical validity of health surveys.
Supporting Evidence
- The study highlights the importance of selecting clusters that represent the population's health characteristics.
- Using a two-stage selection process can enhance the reliability of health survey results.
- Stratification by urbanization level was crucial for ensuring representative sampling.
Takeaway
This study shows that picking specific areas for health surveys can help get better information about health in a city.
Methodology
A two-stage selection procedure was used, starting with a non-random selection of clusters based on health determinants.
Potential Biases
Potential bias from non-random selection of clusters may affect the generalizability of the results.
Limitations
The study faced challenges due to the lack of available health data prior to the survey.
Participant Demographics
Participants included children aged 6 months to less than 6 years and adults aged 35 years and above.
Statistical Information
Confidence Interval
95% CI of +/- 2.3% around a prevalence of 10% at the stratum scale.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website