Analysis of Hierarchical Bayesian Models for Large Space Time Data of the Housing Prices in Tehran

Housing price data is correlated to their location in different neighborhoods and their correlation is type of spatial (location). The price of housing is varius in different months, so they also have a time correlation. Spatio-temporal models are used to analyze this type of the data. An important purpose of reviewing this type of the data is to fit a suitable model for the spatial-temporal analysis, to obtain the parameter estimates and predictions in known sites and times. In this paper, the Gaussian process, the autoregressive and the dynamic  models for large space time data of the housing prices in Tehran is considered.The Bayesian approach is used to fit the models, to predict in new sites and  to forecast in future periods for the housing prices in Tehran.The suitable model with the mean square error of prediction and the computation time will be introduced. Finally prediction map of the housing prices for Tehran in the last months of 1394 is presented.