ABSTRACT Pitman's measure of closeness and mean square error of prediction are two well-known criteria for comparison between estimators and also between predictors. In a stationary first order multiplicative spatial… Click to show full abstract
ABSTRACT Pitman's measure of closeness and mean square error of prediction are two well-known criteria for comparison between estimators and also between predictors. In a stationary first order multiplicative spatial autoregressive model, interpolation and extrapolation are compared based on these two criteria. A wide class of different innovation types are also studied containing Gaussian, exponential, asymmetric Laplace and extended skew t distributions.
               
Click one of the above tabs to view related content.