Best unbiased prediction for Gaussian and log-Gaussian processes
Dennis D. Cox · Lecture notes-monograph series · 2004
The best linear unbiased predictor for a stochastic process is the best unbiased predictor (i.e., the linearity constraint is removed) if the process is Gaussian.This provides a stronger justification for the universal kriging predictor than is generally offered.For log-Gaussian processes, we show that the standard predictor is optimal among all unbiased predictors with respect to a weighted mean squared error prediction criterion.