Don't spin the pen: two alternative methods for second-stage sampling in urban cluster surveys
2007

Alternative Methods for Household Selection in Surveys

Sample size: 30 publication Evidence: moderate

Author Information

Author(s): Rebecca F Grais, Angela MC Rose, Jean-Paul Guthmann

Primary Institution: Epicentre

Hypothesis

Can alternative methods for selecting the first household in urban cluster surveys reduce bias and improve efficiency compared to the traditional spin-the-pen method?

Conclusion

The sampling grid method was found to be the fastest and easiest for field survey teams, while the GPS method was also effective with proper training.

Supporting Evidence

  • The spin-the-pen method was the most complicated and time-consuming.
  • The sampling grid method was accomplished in the least amount of time.
  • The GPS method received positive feedback but had navigation challenges in dense urban areas.

Takeaway

This study looked at different ways to pick the first house to survey in a neighborhood, finding that using a grid or GPS is quicker and easier than the old method of spinning a pen.

Methodology

The study compared three methods for selecting the first household in urban cluster surveys: spinning a pen, using a GPS point, and a sampling grid.

Potential Biases

The traditional method may favor households near the center of the cluster, leading to biased estimates.

Limitations

The study was limited to urban areas and may not be applicable to rural settings where household density varies significantly.

Participant Demographics

The study was conducted in Maradi, Niger, involving urban neighborhoods with varying household densities.

Digital Object Identifier (DOI)

10.1186/1742-7622-4-8

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication