ABSTRACT: Forecasting multiple dependent zero-inflated count processes is a problem encountered in many statistical applications. Standard parametric approaches typically rely on independence assumptions that fail to capture dependence structures. Here a Bayesian nonparametric approach is proposed to overcome this problem and showcased on a real dataset of civil conflicts in Asia. The forecasting model is obtained by generalizing the clustering methods proposed in Franzolini et al. (2023).

Franzolini, B., Bondi, L., Fasano, A., Rebaudo, G. (2023). Bayesian forecasting of multivariate longitudinal zero-inflated counts: an application to civil conflict. In P. Coretto, G. Giordano, M. La Rocca, M.L. Parrella, C. Rampichini (a cura di), CLADAG 2023 - Book of abstracts and short papers (pp. 465-468). Pearson.

Bayesian forecasting of multivariate longitudinal zero-inflated counts: an application to civil conflict

Franzolini, Beatrice;
2023

Abstract

ABSTRACT: Forecasting multiple dependent zero-inflated count processes is a problem encountered in many statistical applications. Standard parametric approaches typically rely on independence assumptions that fail to capture dependence structures. Here a Bayesian nonparametric approach is proposed to overcome this problem and showcased on a real dataset of civil conflicts in Asia. The forecasting model is obtained by generalizing the clustering methods proposed in Franzolini et al. (2023).
Capitolo o saggio
clustering, enriched Dirichlet, excess of zeros, mixtures of finite mixtures, rare events;
English
CLADAG 2023 - Book of abstracts and short papers
Coretto, P; Giordano, G; La Rocca, M; Parrella, ML; Rampichini, C
2023
9788891935632
Pearson
465
468
Franzolini, B., Bondi, L., Fasano, A., Rebaudo, G. (2023). Bayesian forecasting of multivariate longitudinal zero-inflated counts: an application to civil conflict. In P. Coretto, G. Giordano, M. La Rocca, M.L. Parrella, C. Rampichini (a cura di), CLADAG 2023 - Book of abstracts and short papers (pp. 465-468). Pearson.
none
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/582148
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
Social impact