TY - JOUR
T1 - A joint modeling approach for spatial earthquake risk variations
AU - Chen, Chun Shu
AU - Yang, Hong Ding
N1 - Funding Information:
This work was supported by the National Science Council of Taiwan under Grant NSC 98-2118-M-018-003-MY2. The authors thank the editor, the associate editor, the two anonymous referees, and Research Fellow Hsin-Cheng Huang, Institute of Statistical Science, Academia Sinica, Taipei, Taiwan, for helpful comments and suggestions. The authors also thank Professor Yuh-Ing Chen, Institute of Statistics, National Central University, Chungli, Taiwan, for supplying the Chi-Chi earthquake data set.
PY - 2011/8
Y1 - 2011/8
N2 - Modeling spatial patterns and processes to assess the spatial variations of data over a study region is an important issue in many fields. In this paper, we focus on investigating the spatial variations of earthquake risks after a main shock. Although earthquake risks have been extensively studied in the literatures, to our knowledge, there does not exist a suitable spatial model for assessing the problem. Therefore, we propose a joint modeling approach based on spatial hierarchical Bayesian models and spatial conditional autoregressive models to describe the spatial variations in earthquake risks over the study region during two periods. A family of stochastic algorithms based on a Markov chain Monte Carlo technique is then performed for posterior computations. The probabilistic issue for the changes of earthquake risks after a main shock is also discussed. Finally, the proposed method is applied to the earthquake records for Taiwan before and after the Chi-Chi earthquake.
AB - Modeling spatial patterns and processes to assess the spatial variations of data over a study region is an important issue in many fields. In this paper, we focus on investigating the spatial variations of earthquake risks after a main shock. Although earthquake risks have been extensively studied in the literatures, to our knowledge, there does not exist a suitable spatial model for assessing the problem. Therefore, we propose a joint modeling approach based on spatial hierarchical Bayesian models and spatial conditional autoregressive models to describe the spatial variations in earthquake risks over the study region during two periods. A family of stochastic algorithms based on a Markov chain Monte Carlo technique is then performed for posterior computations. The probabilistic issue for the changes of earthquake risks after a main shock is also discussed. Finally, the proposed method is applied to the earthquake records for Taiwan before and after the Chi-Chi earthquake.
KW - Conditional autoregressive model
KW - Hierarchical bayesian model
KW - Markov chain monte carlo
KW - Metropolis-hastings algorithm
UR - http://www.scopus.com/inward/record.url?scp=79958786898&partnerID=8YFLogxK
U2 - 10.1080/02664763.2010.529883
DO - 10.1080/02664763.2010.529883
M3 - 期刊論文
AN - SCOPUS:79958786898
SN - 0266-4763
VL - 38
SP - 1733
EP - 1741
JO - Journal of Applied Statistics
JF - Journal of Applied Statistics
IS - 8
ER -