SEQUENTIAL MODEL CRITICISM IN PROBABILISTIC EXPERT SYSTEMS

Probabilistic expert systems based on Bayesian networks require initial specification of both qualitative graphical structure and quantitative conditional probability assessments. As (possibly incomplete) data accumulate on real cases, the parameters of the system may adapt, but it is also essential that the initial specifications are monitored with respect to their predictive performance. We present a range of monitors based on standardized scoring rules that are designed to detect both qualitative and quantitative departures from the specified model. A simulation study demonstrates the efficacy these monitors at uncovering such departures.