Prior Sensitivity Analysis in a Semi-Parametric Integer-Valued Time Series Model
We examine issues of prior sensitivity in a semi-parametric hierarchical extension of the INAR(<i>p</i>) 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 s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/22/1/69 |
| _version_ | 1811304567160176640 |
|---|---|
| author | Helton Graziadei Antonio Lijoi Hedibert F. Lopes Paulo C. Marques F. Igor Prünster |
| author_facet | Helton Graziadei Antonio Lijoi Hedibert F. Lopes Paulo C. Marques F. Igor Prünster |
| author_sort | Helton Graziadei |
| collection | DOAJ |
| description | We examine issues of prior sensitivity in a semi-parametric hierarchical extension of the INAR(<i>p</i>) 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(<i>p</i>) model. |
| first_indexed | 2024-04-13T08:09:30Z |
| format | Article |
| id | doaj.art-d14c978bea5f475598ddb642ef58e4ff |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-13T08:09:30Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-d14c978bea5f475598ddb642ef58e4ff2022-12-22T02:55:04ZengMDPI AGEntropy1099-43002020-01-012216910.3390/e22010069e22010069Prior Sensitivity Analysis in a Semi-Parametric Integer-Valued Time Series ModelHelton Graziadei0Antonio Lijoi1Hedibert F. Lopes2Paulo C. Marques F.3Igor Prünster4Instituto de Matemática e Estatística, Universidade de São Paulo, São Paulo 05508-090, BrazilDepartment of Decision Sciences and BIDSA, Bocconi University, via Röntgen 1, 20136 Milano, ItalyInsper Institute of Education and Research, Rua Quatá 300, São Paulo 04546-042, BrazilInsper Institute of Education and Research, Rua Quatá 300, São Paulo 04546-042, BrazilDepartment of Decision Sciences and BIDSA, Bocconi University, via Röntgen 1, 20136 Milano, ItalyWe examine issues of prior sensitivity in a semi-parametric hierarchical extension of the INAR(<i>p</i>) 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(<i>p</i>) model.https://www.mdpi.com/1099-4300/22/1/69time series of countsbayesian hierarchical modelingbayesian nonparametricspitman–yor processprior sensitivityclusteringbayesian forecasting |
| spellingShingle | Helton Graziadei Antonio Lijoi Hedibert F. Lopes Paulo C. Marques F. Igor Prünster Prior Sensitivity Analysis in a Semi-Parametric Integer-Valued Time Series Model Entropy time series of counts bayesian hierarchical modeling bayesian nonparametrics pitman–yor process prior sensitivity clustering bayesian forecasting |
| title | Prior Sensitivity Analysis in a Semi-Parametric Integer-Valued Time Series Model |
| title_full | Prior Sensitivity Analysis in a Semi-Parametric Integer-Valued Time Series Model |
| title_fullStr | Prior Sensitivity Analysis in a Semi-Parametric Integer-Valued Time Series Model |
| title_full_unstemmed | Prior Sensitivity Analysis in a Semi-Parametric Integer-Valued Time Series Model |
| title_short | Prior Sensitivity Analysis in a Semi-Parametric Integer-Valued Time Series Model |
| title_sort | prior sensitivity analysis in a semi parametric integer valued time series model |
| topic | time series of counts bayesian hierarchical modeling bayesian nonparametrics pitman–yor process prior sensitivity clustering bayesian forecasting |
| url | https://www.mdpi.com/1099-4300/22/1/69 |
| work_keys_str_mv | AT heltongraziadei priorsensitivityanalysisinasemiparametricintegervaluedtimeseriesmodel AT antoniolijoi priorsensitivityanalysisinasemiparametricintegervaluedtimeseriesmodel AT hedibertflopes priorsensitivityanalysisinasemiparametricintegervaluedtimeseriesmodel AT paulocmarquesf priorsensitivityanalysisinasemiparametricintegervaluedtimeseriesmodel AT igorprunster priorsensitivityanalysisinasemiparametricintegervaluedtimeseriesmodel |