Stationarity conditions for the spatial first-order and serial second-order model

The stationarity conditions for a spatial first-order and serial second-order model in the presence of time-lagged spatial interactions are discussed. The stationarity conditions for serial autoregressive parameters were found on the basis of the structural vector autoregression form of the model. The temporal stationarity was a function of the spatial autoregressive parameters. The value of the time-lagged spatial autoregressive parameter defined the shift of the interval for the first-order serial parameter. However, the sizes of intervals for the values of both serial parameters depended only on the value of the simultaneous autoregressive parameter. Copyright Springer-Verlag 2013