SAMPLING IMPORTANCE RE-SAMPLING FOR NONLINEAR BAYESIAN DYNAMIC MODELS
Lifeng Gao · Journal of Mathematics · 2012
In this paper,the random simulation of Bayesian dynamic models(BDMs) is investigated.With wider assumptions for prior distribution,we exert the sampling importance re-sampling(SIR) to yield all samples instead of original distributions that can make the posterior inferences,the observation predictions,and the model selection.Based on our method,BDMS can be used in more fields.