A Bayesian-Decision Theoretic Approach to Model Error Modeling

This paper takes a Bayesian-decision theoretic approach to transfer function\ud estimation, nominal model estimation, and quantification of the resulting model error.\ud Consistency of the nonparametric estimate of the transfer function is proved together with a rate of convergence. The required quantities can be computed routinely using reversible jump Markov chain Monte Carlo methods. The proposed methodology has connections with set membership identification which has been extensively studied for this problem