Critical infrastructure Empirical Bayes inference with nonlinear homogenizations and correlated intensity functions: Use in asset degradation modelling

To address this challenge we develop a new method of estimation drawing upon the principles of empirical Bayes inference (Carlin and Louis, 2000; Efron, 2005; Quigley and Walls, 2011). Our proposed method is distinctive because we need to develop an appropriate means of homogenising the pooled asset experience data to support better estimation when the underlying failure intensity function is dynamic. We also need to capture the relationships that may exist between the asset degradation rates due to the environmental conditions to which they are exposed.