THE BIAS OF ESTIMATORS OF CAUSAL SPATIAL AUTOREGRESSIVE PROCESSES

We study the asymptotic distribution of Yule-Walker and least squares estimators for two-dimensional causal autoregressive processes observe d on a rectangular part of a lattice. An explicit expression for the a symptotic bias of Yule-Walker estimators is obtained. It is shown that this bias disappears if we use the so-called unbiased sample autocova riance function or least squares estimators.