Article accepted in the Annals of Statistics

About

The article Necessary and sufficient conditions for asymptotically optimal linear prediction of random fields on compact metric spaces by K. Kirchner and D. Bolin has been accepted for publication in the Annals of Statistics.

For statistical applications it is crucial to understand the effect that misspecifying the mean or the covariance function of a random field has on linear prediction. In the article, we address this by providing three necessary and sufficient conditions for uniformly asymptotically optimal linear prediction of random fields on compact metric spaces.