Abstract
We examine issues of prior sensitivity in a semi-parametric hierarchical extension of the INAR(p) model with innovation rates clustered according to a Pitman-Yor process placed at the top of the model hierarchy. Our main finding is a graphical criterion that guides the specification of the hyperparameters of the Pitman-Yor process base measure. We show how the discount and concentration parameters interact with the chosen base measure to yield a gain in terms of the robustness of the inferential results. The forecasting performance of the model is exemplified in the analysis of a time series of worldwide earthquake events, for which the new model outperforms the original INAR(p) model.
Original language | English (US) |
---|---|
Pages (from-to) | 69 |
Number of pages | 1 |
Journal | Entropy |
Volume | 22 |
Issue number | 1 |
DOIs | |
State | Published - Jan 1 2020 |
Externally published | Yes |
Keywords
- Bayesian forecasting
- Bayesian hierarchical modeling
- Bayesian nonparametrics
- Clustering
- Pitman-Yor process
- Prior sensitivity
- Time series of counts
ASJC Scopus subject areas
- Information Systems
- Mathematical Physics
- Physics and Astronomy (miscellaneous)
- Electrical and Electronic Engineering