607 – New Models for Spatial and Demographic Longitudinal Data
Spatial Aggregation of STAR(1,1) Models
Andrew Gehman
William W. S Wei
Temple University
In this paper, we demonstrate that in most cases the spatial aggregate of spatial time series data contains similar properties to the non-aggregate. In particular, we examine the space-time autoregressive model of temporal and spatial lag 1 (the STAR(1,1) model) and through a simulation study see that even when the condition of poolability does not hold, the aggregate can usually be modeled as a STAR(1,1) model with only slightly higher forecast error. The parameters of the aggregate STAR(1,1) model are also derived and shown to be functions of the non-aggregate parameters. Future work will be to generalize these results to other types of STARMA models.