Previous |  Up |  Next

Article

Title: Gaussian approximation for functionals of Gibbs particle processes (English)
Author: Flimmel, Daniela
Author: Beneš, Viktor
Language: English
Journal: Kybernetika
ISSN: 0023-5954 (print)
ISSN: 1805-949X (online)
Volume: 54
Issue: 4
Year: 2018
Pages: 765-777
Summary lang: English
.
Category: math
.
Summary: In the paper asymptotic properties of functionals of stationary Gibbs particle processes are derived. Two known techniques from the point process theory in the Euclidean space $\mathbb{R}^d$ are extended to the space of compact sets on $\mathbb{R}^d$ equipped with the Hausdorff metric. First, conditions for the existence of the stationary Gibbs point process with given conditional intensity have been simplified recently. Secondly, the Malliavin-Stein method was applied to the estimation of Wasserstein distance between the Gibbs input and standard Gaussian distribution. We transform these theories to the space of compact sets and use them to derive a Gaussian approximation for functionals of a planar Gibbs segment process. (English)
Keyword: asymptotics of functionals
Keyword: innovation
Keyword: stationary Gibbs particle process
Keyword: Wasserstein distance
MSC: 60D05
MSC: 60G55
idZBL: Zbl 06987033
idMR: MR3863255
DOI: 10.14736/kyb-2018-4-0765
.
Date available: 2018-10-30T14:49:56Z
Last updated: 2020-01-05
Stable URL: http://hdl.handle.net/10338.dmlcz/147423
.
Reference: [1] Beneš, V., Večeřa, J., Pultar, M.: Planar segment processes with reference mark distributions, modeling and simulation..Methodol. Comput. Appl. Probab. (2018), accepted. 10.1007/s11009-017-9608-x
Reference: [2] Blaszczyszyn, B., Yogeshwaran, D., Yukich, J. E.: Limit theory for geometric statistics of point processes having fast decay of correlations..Preprint (2018), submitted to the Annals of Probab.
Reference: [3] Daley, D. J., Vere-Jones, D.: An Introduction to the Theory of Point Processes..Volume I: Elementary Theory and Methods. MR 1950431
Reference: [4] Dereudre, D.: Introduction to the theory of Gibbs point processes..Preprint (2017), submitted.
Reference: [5] Georgii, H.-O.: Gibbs Measures and Phase Transitions. Second edition..W. de Gruyter and Co., Berlin 2011. MR 2807681, 10.1515/9783110250329
Reference: [6] Last, G., Penrose, M.: Lectures on the Poisson Process..Cambridge University Press, Cambridge 2017. MR 3791470, 10.1017/9781316104477
Reference: [7] Mase, S.: Marked Gibbs processes and asymptotic normality of maximum pseudo-likelihood estimators..Math. Nachr. 209 (2000), 151-169. MR 1734363, 10.1002/(sici)1522-2616(200001)209:1<151::aid-mana151>3.0.co;2-j
Reference: [8] Ruelle, D.: Superstable interactions in classical statistical mechanics..Commun. Math. Phys. 18 (1970), 127-159. MR 0266565, 10.1007/bf01646091
Reference: [9] Schneider, R., Weil, W.: Stochastic and Integral Geometry..Springer, Berlin 2008. Zbl 1175.60003, MR 2455326, 10.1007/978-3-540-78859-1
Reference: [10] Schreiber, T., Yukich, J. E.: Limit theorems for geometric functionals of Gibbs point processes..Ann. Inst. Henri Poincaré - Probab. et Statist. 49 (2013), 1158-1182. MR 3127918, 10.1214/12-aihp500
Reference: [11] Serra, J.: Image Analysis and Mathematical Morphology..Academic Press, London 1982. MR 0753649, 10.1002/cyto.990040213
Reference: [12] Stucki, K., Schuhmacher, D.: Bounds for the probability generating functional of a Gibbs point process..Adv. Appl. Probab. 46 (2014), 21-34. MR 3189046, 10.1239/aap/1396360101
Reference: [13] Torrisi, G. L.: Probability approximation of point processes with Papangelou conditional intensity..Bernoulli 23 (2017), 2210-2256. MR 3648030, 10.3150/16-bej808
Reference: [14] Večeřa, J., Beneš, V.: Approaches to asymptotics for U-statistics of Gibbs facet processes..Statist. Probab. Let. 122 (2017), 51-57. MR 3584137, 10.1016/j.spl.2016.10.024
Reference: [15] Xia, A., Yukich, J. E.: Normal approximation for statistics of Gibbsian input in geometric probability..Adv. Appl. Probab. 25 (2015), 934-972. MR 3433291, 10.1017/s0001867800048965
.

Files

Files Size Format View
Kybernetika_54-2018-4_8.pdf 485.7Kb application/pdf View/Open
Back to standard record
Partner of
EuDML logo