Comparative Judgement Modeling to Map Forced Marriage at Local Levels

Rowland Seymour*, Albert Nyarko-Agyei, Helen McCabe, Katie Severn, David Sirl, Theodore Kypraios, Adam Taylor

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

42 Downloads (Pure)

Abstract

Forcing someone into marriage against their will is a violation of their human rights. In 2021, the county of Nottinghamshire, U.K., launched a strategy to tackle forced marriage and violence against women and girls. We set out to map the risk of forced marriage across the county to support the strategy and enable the development of local interventions. However, there was no centralised database for forced marriage in the county and carrying out a survey using standard survey methods was unlikely to produce robust results due to the hidden nature of this crime. Comparative judgement provides a survey design that can map the risk of forced marriage through pairwise comparisons. Current comparative judgement models require studies to have a large number of participants, so we developed a more flexible spatial modelling structure and a mechanism to schedule comparisons more effectively. The proposed modelling structure reduced the data collection burden and made a comparative judgement study feasible with a small number of participants. Underpinning this structure is a latent variable representation that improves on the scalability of inferential procedures of previous comparative judgement models. We used these methods to map the risk of forced marriage across Nottinghamshire, thereby supporting the county’s strategy for tackling violence against women and girls.
Original languageEnglish
Pages (from-to)419-439
Number of pages21
JournalAnnals of Applied Statistics
Volume19
Issue number1
Early online date4 Nov 2024
DOIs
Publication statusPublished - 17 Mar 2025

Fingerprint

Dive into the research topics of 'Comparative Judgement Modeling to Map Forced Marriage at Local Levels'. Together they form a unique fingerprint.

Cite this