Application of Probability-Based Link-Tracing and Nonprobability Approaches to Sampling Out-of-School Youth in Developing Countries

Abstract

Motivated by the United Nations' Education Sustainable Development Goal of all young people achieving at least basic literacy and numeracy skills, the Organisation for Economic Co-operation and Development has undertaken a pilot study of the Programme for the International Student Assessment (PISA) for developing countries. In this study, PISA is administered in five developing countries to 14- to 16-year olds who are either out of school or in school below grade 7. The target population is about 1-3 percent of the overall population for the participating countries. Several options to achieve adequate representation were presented to countries. To simplify operations, reduce costs, reduce bias, and achieve sample size goals, a probability-based link-tracing approach was designed and attempted in countries as one of the several approaches administered. In this article, we provide an evaluation of the approach and describe its application toward providing proficiency estimates with adequate representation of the target population.