About predictions in spatial autoregressive models: Optimal and almost optimal strategies

We address the problem of prediction in the classical spatial autoregressive LAG model for areal data. In contrast with the spatial econometrics literature, the geostatistical literature has devoted much attention to prediction using the Best Linear Unbiased Prediction approach. From the methodological point of view, we explore the limits of the extension of BLUP formulas in the context of the spatial autoregressive LAG models for in sample prediction as well as out-of-sample prediction simultaneously at several sites. We propose a more tractable “almost best” alternative. From an empirical perspective, we present data-based simulations to compare the efficiency of the classical formulas with the best and almost best predictions. JEL classification: C21, C53