Spatial distribution of the earthquake in Mainland China.

We propose a geoadditive model with spatial random effects to model the earthquake distribution in Mainland China. The error is modeled an infinite mixture of Gaussian distributions with a stochastic constraint that ensures inference on the quantiles of interest. The spatial random effects are used to capture individual area effects which allow for heterogeneity among regions. We run Bayesian quantile regression for the spatial trend of the geoadditive model under a flexible Bayesian framework. The proposed method not only allows for a full span of quantile-restricted error distributions, but also separates a large-scale geographical trend from local spatial correlation. This makes the Bayesian quantile regression feasible and flexible. Our method can be generalized to other applications that involve spatial correlation along irregular contours or in discontinuous spatial domains. Our results demonstrate the usefulness and effectiveness of the proposed methodology. • We propose a geoadditive model with spatial random effects to model the earthquake distribution in Mainland China. • The error is modeled an infinite mixture of Gaussian distributions with a stochastic constraint that ensures inference on the quantiles of interest. The spatial random effects are used to capture individual area effects which allow for heterogeneity among regions. • The proposed method not only allows for a full span of quantile-restricted error distributions, but also separates a large-scale geographical trend from local spatial correlation. [ABSTRACT FROM AUTHOR]