RT Journal Article
T1 Bootstrapping kernel intensity estimation for inhomogeneous point processes with spatial covariates
A1 Borrajo García, María Isabel
A1 González Manteiga, Wenceslao
A1 Martínez Miranda, María Dolores
K1 Spatial point processes
K1 First-order intensity
K1 Kernel estimation
K1 Bandwidth selection
K1 Covariates
AB The bias-variance trade-o  for inhomogeneous point processes with covariatesis theoretically and empirically addressed. A consistent kernel estimatorfor the  rst-order intensity function based on covariates is constructed, whichuses a convenient relationship between the intensity and the density of eventslocation. The asymptotic bias and variance of the estimator are derived andhence the expression of its infeasible optimal bandwidth. Three data-drivenbandwidth selectors are proposed to estimate the optimal bandwidth. Oneof them is based on a new smooth bootstrap proposal which is proved to beconsistent under a Poisson assumption. The other two are a rule-of-thumbmethod based on assuming normallity, and a simple non-model-based approach.An extensive simulation study is accomplished considering Poissonand non-Poisson scenarios, and including a comparison with other competitors.The practicality of the new proposals is shown through an applicationto real data about wild res in Canada, using meteorological covariates
PB Elsevier
SN 0167-9473
YR 2019
FD 2019
LK http://hdl.handle.net/10347/20314
UL http://hdl.handle.net/10347/20314
LA eng
NO Borrajo, M. I., González-Manteiga, W., & Martínez-Miranda, M. D. (2020). Bootstrapping kernel intensity estimation for inhomogeneous point processes with spatial covariates. Computational Statistics & Data Analysis, 144
NO This is the accepted manuscript of the following article: Borrajo, M., González-Manteiga, W., & Martínez-Miranda, M. (2020). Bootstrapping kernel intensity estimation for inhomogeneous point processes with spatial covariates. Computational Statistics & Data Analysis, 144, 106875. doi: 10.1016/j.csda.2019.106875
NO This work has been partially supportedby the Spanish Ministry of Economy and Competitiveness, through grantsnumber MTM2013-41383P and MTM2016-76969P, which includes supportfrom the European Regional Development Fund (ERDF). Support from theIAP network StUDyS from Belgian Science Policy (P6/07), is also acknowledged.M.I. Borrajo has been supported by FPU grant (FPU2013/00473)from the Spanish Ministry of Education
DS Minerva
RD 26 abr 2026