Answers are grounded in this paper and cite their sources.
In this article we present prediction methods for recurrent events that occur for individuals or units in some population. The events are modeled using flexible nonhomogeneous Poisson processes, and possible heterogeneity among the individuals is modeled using random effects. We also present effective calibration techniques that provide prediction intervals with coverage probabilities close to a desired nominal level. We apply these methods to a particular warranty data setting from the automobile industry. The number of processes in this context being very large, we emphasize methods providing rapid computation of prediction intervals.
No takes yet. Share an insight, caveat, or question.
Frédette et al. (2007) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: