gridsample: Tools for Grid-Based Survey Sampling Design

Multi-stage cluster household surveys are commonly performed by governments and programs to monitor population demographic, social, economic, and health outcomes. In these surveys, communities are sampled in a first stage of sampling from within subpopulations of interest (or strata), households are sampled in a second stage of sampling, and sometimes individuals are listed and further sampled within households. The first stage of sampling, where communities of sample populations are defined, are called Primary Sampling Units (PSUs) while the households are secondary sampling units (SSUs). Census data are typically used to select PSUs within strata. If census data are outdated, inaccurate, or not available at fine enough scale, however, gridded population data can be used instead. This tool selects PSUs within user-defined strata using gridded population data, given desired numbers of sampled households within each PSU. The population densities used to create PSUs are drawn from rasters such as the population data from the WorldPop Project ( PSUs are defined within a stratum using a serpentine sampling method, and can be set to have a certain ratio of urban and rural PSUs, or to be evenly distributed across a coarse, user-defined grid.

AuthorDana R. Thomson (University of Southampton), Nick W. Ruktanonchai (University of Southampton), Forrest R. Stevens (University of Louisville), Marcia Castro (Harvard University), Andrew J. Tatem (University of Southampton)
Date of publication2016-11-30 15:22:40
MaintainerNick Ruktanonchai <>
LicenseMIT + file LICENSE

View on CRAN

Questions? Problems? Suggestions? or email at

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.