A Computational Architecture for N-Way Sensitivity Analysis of Bayesian Networks
Veerle M.H. Coupé, Finn Verner Jensen, Uffe B. Kjærulff, Linda C. van der Gaag · 2000
The relation between a probability computed from a Bayesian network and the parameters in the network is a simple mathematical function. Any prior probability can be expressed as a multilinear function in the network's parameters; any posterior probability is a quotient of such functions. These functions serve to yield insight into the robustness of a Bayesian network. To this end, it suffices to establish the coefficients in the functions. In general, the investigation into the relation between a probability computed from the network and the network's parameters is called a sensitivity analysis. In the past, various methods for sensitivity analysis have been suggested, most of them being computationally very expensive. In this paper, a new method is presented, that is both elegant and efficient. The method builds upon a junction tree representation of a Bayesian network for its computational architecture. Basically, the method amounts to the propagation of vectors of coeffi...