In this paper Ne use posterior covariance matrices to study the strong
consistency of Bayes estimators in stochastic regression models under
various assumptions on the stochastic regressors. The random errors a
re assumed to form a martingale difference sequence. Several results a
re obtained using a recursion satisfied by the sequence of posterior c
ovariance matrices. These results suggest that the posterior covarianc
e matrix is a useful tool in studying strong consistency problems in s
tochastic regression models. Three examples from sequential design and
adaptive control are discussed.