Bayesian nonparametric nonhomogeneous Poisson process with applications to USGS earthquake data

Intensity estimation is a common problem in statistical analysis of spatial point pattern data. This paper proposes nonparametric Bayesian method for estimating the process intensity based on mixture finite (MFM) model. MFM approach leads to consistent and simultaneous estimate surface clustering information (number clusters configurations) subareas surface. An efficient Markov chain Monte Carlo (MCMC) algorithm proposed our method, where it performs marginalization over number which avoids complicated reversible jump MCMC or allocation samplers. Extensive simulation studies are carried out examine empirical performance method. The usage further illustrated with Earthquake Hazards Program United States Geological Survey (USGS) earthquake