Spatial prediction of the mark of a location-dependent marked point process: how the use of a parametric model may improve prediction

Title:

Spatial prediction of the mark of a location-dependent marked point process: how the use of a parametric model may improve prediction

Creator:

Mrkvička, Tomáš, Goreaud, François, and Chadœuf, Joël

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:faf032e7-c0cb-4158-91ee-1ea4eaf498fc
uuid:faf032e7-c0cb-4158-91ee-1ea4eaf498fc

Subject:

kernel estimation, marked Poisson process, mean mark estimation, location-dependent mark distribution, and segment process

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

We discuss the prediction of a spatial variable of a multivariate mark composed of both dependent and explanatory variables. The marks are location-dependent and they are attached to a point process. We assume that the marks are assigned independently, conditionally on an unknown underlying parametric field. We compare (i) the classical non-parametric Nadaraya-Watson kernel estimator based on the dependent variable (ii) estimators obtained under an assumption of local parametric model where explanatory variables of the local model are estimated through kernel estimation and (iii) a kernel estimator of the result of the parametric model, supposed here to be a Uniformly Minimum Variance Unbiased Estimator derived under the local parametric model when complete and sufficient statistics are available. The comparison is done asymptotically and by simulations in special cases. The procedure for better estimator selection is then illustrated on a real-life data set.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Coverage:

[696]-714

Source:

Kybernetika | 2011 Volume:47 | Number:5

Harvested from:

CDK

Metadata only:

false