(cze): The increasing spatial complexity of modern adaptive wireless and sensor networks and the diversity of its elements call for reliable estimation of several variables of interest. In most regular cases it can be naturally assumed that each participating element carries (to some degree) valid information about these variables and that they could potentially benefit from cooperation and information sharing. We will refer to this modus operandi as the distributed estimation.The basic setting of the decentralized estimation method put the following limitation on the internodal communication: it divides the network into smaller overlapping units consisting of a node and its adjacent neighbours. This node is allowed to exchange data only within its closed neighbourhood. The Bayesian formulation of the problem and its solution abstracts from any particular model case.