From hidden populations to social structure
To situate the sixteen articles included in this Special issue on the Network Scale-Up Method (NSUM) and Aggregated Relational Data (ARD), we synthesise nearly four decades of research in the field. Drawing on 301 studies, we introduce key concepts and trace major trends, including the shift from hi...
| Autores: | , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2026 |
| País: | España |
| Institución: | Universitat Autònoma de Barcelona |
| Repositorio: | Dipòsit Digital de Documents de la UAB |
| Idioma: | inglés |
| OAI Identifier: | oai:dnet:uabarcelona_::9ddb9d6f011bbaed2f8b30ed9a015132 |
| Acceso en línea: | https://ddd.uab.cat/record/328264 https://dx.doi.org/urn:doi:10.1016/j.socnet.2026.04.002 |
| Access Level: | acceso abierto |
| Palabra clave: | Network Scale-Up Method Aggregated Relational Data Acquaintanceship Networks Personal Networks Hard-to-count Populations Survey Design SDG 3 - Good Health and Well-being |
| Sumario: | To situate the sixteen articles included in this Special issue on the Network Scale-Up Method (NSUM) and Aggregated Relational Data (ARD), we synthesise nearly four decades of research in the field. Drawing on 301 studies, we introduce key concepts and trace major trends, including the shift from hidden population estimation to the analysis of extended personal networks. We also reassess claims of NSUM's unsatisfactory performance in public health, showing that many evaluations rely on earlier implementations rather than more advanced estimation models. In addition, we identified major surveys and software supporting NSUM and ARD, including recent large-scale datasets, to compare how these methods have been implemented across studies. Throughout the review, we offer practical guidance, including new suggestions regarding the need to select coherent sets of probe groups. Because design issues are not always well documented, we also propose a reporting checklist to enhance transparency and comparability. Finally, we show that the sixteen articles included in this Special Issue engage directly with the issues raised in this review, addressing biases, refining estimation models, analysing acquaintanceship networks, and demonstrating how NSUM outputs can inform agent-based models. |
|---|