Published online by Cambridge University Press: 19 October 2020
Despite extensive research on international norms, our approach to measurement has not kept pace with theoretical advancements. Existing research often relies on single indicators to facilitate cross-national analysis or employs case-study designs that provide greater nuance but restricted scope. Given these limitations, this note argues that item-response theory (IRT) provides a framework for strengthening the link between our theoretical understanding of norms and empirical measurement of norm adoption. In turn, I develop a modified Bayesian model with substantively informed dynamic priors. The proposed approach is evaluated with the lesbian, gay, and bisexual (LGB) equality norm, using 13 policies and laws across 196 countries (1990–2017). The results are broadly consistent with theoretical expectations while also providing new empirical evidence on the evolution of the norm across space and time. This note highlights the significant potential in greater interaction between both latent measurement approaches and scholarship on international norms.
Previous versions of the paper were presented at the 2019 Meeting of the Canadian Political Science Association and the 2019 Meeting of the British International Studies Association. The author would especially like to thank Dave Armstrong, Adam Enders, Erin Hannah, Adam Harmes, and Matt Lebo for invaluable support, as well as the anonymous reviewers and the editors of APSR for their insightful comments and suggestions that substantially improved the paper. Replication materials are available at the American Political Science Review Dataverse: https://doi.org/10.7910/DVN/XS4P50.