Intensity estimation for spatial point processes observed with noise

被引:12
|
作者
Cucala, Lionel [1 ]
机构
[1] Univ Toulouse 3, Lab Stat & Probabilites, UMR C5583, Inst Math, F-31062 Toulouse 9, France
关键词
deconvolution; kernel density estimation; measurement error; spatial point processes;
D O I
10.1111/j.1467-9469.2007.00583.x
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
This article introduces a kernel estimator of the intensity function of spatial point processes taking into account location errors. The asymptotic properties of the estimator are derived and a bandwidth selection procedure is described. A simulation study compares our results with that of the classical kernel estimator and shows that the edge-corrected deconvoluting kernel estimator is more appropriate.
引用
收藏
页码:322 / 334
页数:13
相关论文
共 50 条