Big Data Meets Survey Science

20Worldwide Population Estimates for Small Geographic Areas: Can We Do a Better Job?

Safaa Amer¹, Dana Thomson^2,3, Rob Chew¹, and Amy Rose⁴

¹RTI International, Research Triangle Park, NC, USA

²WorldPop, University of Southampton, UK

³Flowminder Foundation, Stockholm, Sweden

⁴Oak Ridge National Laboratory, Oak Ridge, TN, USA

20.1 Introduction

Conducting surveys in low‐ and middle‐income countries (LMICs) is particularly challenging because many areas lack a complete sampling frame, have outdated census information, or have limited data available for designing and selecting a representative sample. Fortunately, with developments in geographic information systems (GISs), remote sensing, and machine learning, tools have emerged to disaggregate and update the distribution of census data to support survey sampling methodology and improve population estimates. In this chapter, we discuss the basis for these population estimates, scope, and limitations based on experiences in development of massive global population datasets and usage of these datasets as a basis for sampling design. We also present tools and approaches for using these georeferenced population estimates for complex household survey sampling (i.e. Geo‐Sampling, GridSample R, and GridSample2.0). Finally, we discuss challenges with geographic population distributional assumptions within these georeferenced areas that are operationally relevant for conducting household surveys in LMICs, with approaches to help address ...