The paper addresses the issue of testing separability of spatio-temporal locations and functional marks in spatio-temporal functional marked point processes (STFMPPs), where spatio-temporal events are associated with marks evolving along a lifetime domain. Separability assumptions are generally adopted to simplify inference, while tools to assess their validity in the presence of functional marks are lacking. We propose a separability test based on a finite-dimensional score representation of functional marks. Simulation studies and an application to seismic data show that the test effectively detects departures from separability.
Lo Galbo, G. (2026). Testing Separability in Spatio-Temporal Functional Marked Point Processes. In F. Martella, S. Arima, M.F. Marino, C. Mollica (a cura di), Statistical Science: From Theory to Applied Research (pp. 551-557). Springer, Cham [10.1007/978-3-032-30881-8_89].
Testing Separability in Spatio-Temporal Functional Marked Point Processes
Lo Galbo, Giada
Primo
2026-07-17
Abstract
The paper addresses the issue of testing separability of spatio-temporal locations and functional marks in spatio-temporal functional marked point processes (STFMPPs), where spatio-temporal events are associated with marks evolving along a lifetime domain. Separability assumptions are generally adopted to simplify inference, while tools to assess their validity in the presence of functional marks are lacking. We propose a separability test based on a finite-dimensional score representation of functional marks. Simulation studies and an application to seismic data show that the test effectively detects departures from separability.| File | Dimensione | Formato | |
|---|---|---|---|
|
978-3-032-30881-8_89.pdf
Solo gestori archvio
Descrizione: Capitolo versione editoriale
Tipologia:
Versione Editoriale
Dimensione
691.69 kB
Formato
Adobe PDF
|
691.69 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
|
Giada_Lo_Galbo___SIS_FENStatS_2026.pdf
Solo gestori archvio
Descrizione: Contributo versione post-print
Tipologia:
Post-print
Dimensione
5.72 MB
Formato
Adobe PDF
|
5.72 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


