Bayesian estimation of Cox model with non-nested random effects: an application to the ratification of ILO conventions by developing countries

We use a multivariate hazard model for the analysis of data on the timing of ratifications of different conventions. The model accounts for two random effects, one at the country level and the other at the convention level. We use a semi-parametric Bayesian approach, based on the partial likelihood. Our findings confirm the results of preceding studies that ratification behaviour varies substantially across members states and conventions. Furthermore, the results yield insights on the impact of unobserved heterogeneity on the ratification process.