Choosing a survey sample when data on the population are limited: a method using Global Positioning Systems and aerial and satellite photographs
1 Department of Clinical Epidemiology and Biostatistics, McMaster University, CRL-221, 1280 Main St West, Hamilton, ON, Canada, L8S 4K1
2 School of Social Work, Wayne State University, Detroit, Michigan, USA
3 Social Work and Political Science, University of Michigan, Ann Arbor, Michigan, USA
4 Faculty of Health Sciences, Simon Fraser University, Burnaby, Canada
5 Present address: Boise State University, Boise, Idaho, USA
Emerging Themes in Epidemiology 2012, 9:5 doi:10.1186/1742-7622-9-5Published: 11 September 2012
Various methods have been proposed for sampling when data on the population are limited. However, these methods are often biased. We propose a new method to draw a population sample using Global Positioning Systems and aerial or satellite photographs.
We randomly sampled Global Positioning System locations in designated areas. A circle was drawn around each location with radius representing 20 m. Buildings in the circle were identified from satellite photographs; one was randomly chosen. Interviewers selected one household from the building, and interviews were conducted with eligible household members.
Participants had known selection probabilities, allowing proper estimation of parameters of interest and their variances. The approach was made possible by recent technological developments and access to satellite photographs.