Small area estimation using unmatched sampling and linking models

The authors use a hierarchical Bayes approach to area level unmatched sampling and linking models for small area estimation. Empirically they compare inferences under unmatched models with those obtained under the customary matched sampling and linking models. They apply the proposed method to Canadian census undercoverage estimation, developing a full hierarchical Bayes approach using Markov Chain Monte Carlo sampling methods. They show that the method can provide efficient model-based estimates. They use posterior predictive distributions to assess model fit.