search for


Analysis of domestic diabetes prevalence data using Bayesian spatially-dependent clustering models in regression coefficients
Journal of the Korean Data & Information Science Society 2018;29:633-44
Published online May 31, 2018
© 2018 Korean Data and Information Science Society.

Sojin Hong1 · Dayun Kang2 · Jungsoon Choi3

12Department of Applied Statistics, Hanyang University
3Department of Mathematics, Hanyang University
Correspondence to: Assistant professor, Department of Mathematics, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, South Korea. E-mail:
Received September 20, 2017; Revised May 4, 2018; Accepted May 14, 2018.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
In spatial regression modeling, it is commonly assumed that spatial random components are considered to explain the spatial dependency structures and regression coefficient is constant over the entire spatial domain. However, the regression coefficient may have spatial dependency structures and be different depending on the sub-regions. Recently, Lawson et al. (2014) proposed Bayesian discrete clustering methods of spatially dependent regression coefficients and applied them to cancer survival dataset. Bayesian hierarchical approach was utilized to explain the complicated spatial dependent structures. In this paper, we first analyze the diabetes prevalence data for the entire 252 administrative districts of South Korea in 2014 year using spatially-dependent regression coefficient clustering models. We evaluate the performance of the proposed spatial models with the non-spatial model.
Keywords : Bayesian inference, CHS, clustering, diabetes prevalence rates data, spatial model.