Every few days, we will be publishing layman’s abstracts of new articles from our prestigious portfolio of journals in statistics. The aim is to highlight the latest research to a broader audience in an accessible format.
The article featured today is from the Canadian Journal of Statistics and the full article, published in issue 47.3, is available to read online here.
Torabi, M. (2019), Spatial generalized linear mixed models in small area estimation. Can J Statistics, 47: 426-437. doi: 10.1002/cjs.11502
Policy decisions with respect to the allocation of resources to sub-groups of a population (e.g., health region) depend on “reliable” predictors of their underlying parameters. For instance, in the case of chronic disease or cancer, it is important for policy makers to understand the geographical patterns of disease in order to determine health regions with high risk of disease and establish prevention strategies. However, the literature is spares while dealing with small sample sizes compared to population sizes in some health regions (small areas). In this paper, a general framework for various health outcomes (normal and non-normal) is proposed to accurately predict small area predictors and its precisions. Evaluation of the performance of the proposed approach is completed through simulation studies and by a real application of the models to an esophageal cancer dataset in Minnesota, USA.