Journal of Official Statistics, Vol.21, No.3, 2005. pp. 411–432
Small Area Estimation from the American Community Survey Using a Hierarchical Logistic Model of Persons and Housing Units
Abstract:A multivariate binomial/multinomial model is proposed for estimating poverty and housing-unit characteristics of small areas. The methodology for producing estimates is presented, along with several evaluations using data from the American Community Survey. In one of these evaluations, it is demonstrated that the model produces predicted samples whose within small area design-based estimates of variance are in concordance with the original design-based estimates. It is concluded that this approach can be a viable way to make small area estimates without needing to assume that the design-based estimates of within-small area variance are fixed (as in most area-level models) or that the design-based estimates themselves, are normally distributed. The model introduced proposes a way to incorporate both housing unit information and person level information and may be of use in similar contexts.
Keywords:Hierarchical model, logistic parameterization, unit level small area model, full Bayesian analysis, MCMC, Metropolis/Hastings, Gibbs sampling
Copyright © Statistics Sweden 1996-2018. Open AccessISSN 0282-423XCreated and Maintained by OKS Group