×

zbMATH — the first resource for mathematics

Estimation of the intensity parameter of the germ-grain quermass-interaction model when the number of germs is not observed. (English) Zbl 1309.60004
Summary: The Quermass-interaction model allows to generalize the classical germ-grain Boolean model in adding a morphological interaction between the grains. It enables to model random structures with specific morphologies, which are unlikely to be generated from a Boolean model. The Quermass-interaction model depends in particular on an intensity parameter, which is impossible to estimate from classical likelihood or pseudo-likelihood approaches because the number of points is not observable from a germ-grain set. In this paper, we present a procedure based on the Takacs-Fiksel method, which is able to estimate all parameters of the Quermass-interaction model, including the intensity. An intensive simulation study is conducted to assess the efficiency of the procedure and to provide practical recommendations. It also illustrates that the estimation of the intensity parameter is crucial in order to identify the model. The Quermass-interaction model is finally fitted by our method to P. Diggle’s heather data set.

MSC:
60D05 Geometric probability and stochastic geometry
62F10 Point estimation
60G55 Point processes (e.g., Poisson, Cox, Hawkes processes)
60K35 Interacting random processes; statistical mechanics type models; percolation theory
Software:
spatial
PDF BibTeX XML Cite
Full Text: DOI arXiv
References:
[1] Ambler, Probability and mathematical genetics: papers in honour of Sir John Kingman pp 64– (2010) · doi:10.1017/CBO9781139107174.005
[2] Baddeley, Area-interaction point processes, Ann. Inst. Statist. Math 47 (4) pp 601– (1995) · Zbl 0848.60051 · doi:10.1007/BF01856536
[3] Coeurjolly, Takacs-Fiksel method for stationary marked Gibbs point processes, Scand. J. of Stat. 39 (3) pp 416– (2012) · Zbl 1323.62023 · doi:10.1111/j.1467-9469.2011.00738.x
[4] Cressie, Statistics for spatial data, 2. ed. (1993)
[5] Dereudre, Existence of quermass processes for non locally stable interaction and non bounded convex grains, Adv. Appl. Prob. 41 pp 664– (2009) · Zbl 1179.60003 · doi:10.1239/aap/1253281059
[6] Diggle, Binary mosaics and the spatial pattern of heather, Biometrics 37 pp 531– (1981) · doi:10.2307/2530566
[7] Fiksel, Estimation of interaction potentials of Gibbsian point processes, Statistics 19 pp 77– (1988) · Zbl 0644.62044 · doi:10.1080/02331888808802074
[8] Georgii, Canonical and grand canonical Gibbs states for continuum systems, Commun. Math. Phys. 48 (1) pp 31– (1976) · doi:10.1007/BF01609410
[9] Georgii, Stochastic comparison of point random fields, J. Appl. Prob. 34 pp 868– (1997) · Zbl 0905.60030 · doi:10.2307/3215003
[10] Goulard, Parameter estimation for marked Gibbs point processes through the maximum pseudo-likelihood method, Scand. J. Stat. 23 pp 365– (1996) · Zbl 0861.62058
[11] Hadwiger, Vorlesungen über inhalt, Oberfläche und isoperimetrie (1957) · Zbl 0078.35703 · doi:10.1007/978-3-642-94702-5
[12] Hall, Counting methods for inference in binary mosaics, Biometrics 41 pp 1049– (1985) · doi:10.2307/2530977
[13] Hall, Introduction to the theory of coverage processes (1988) · Zbl 0659.60024
[14] Kendall, Proceedings of the International Symposium on Advances in Theory and Applications of Random Sets pp 105– (1997)
[15] Kendall, Quermass-interaction processes conditions for stability, Adv. Appl. Prob. 31 pp 315– (1999) · Zbl 0962.60026 · doi:10.1239/aap/1029955137
[16] Likos, Statistical morphology of random interface microemulsions, J. Chem. Phys. 102 pp 9350– (1995) · doi:10.1063/1.468802
[17] Mecke, A morphological model for complex fluids, J. Phys. Condens. Matter 8 pp 9663– (1996) · doi:10.1088/0953-8984/8/47/080
[18] Molchanov, Statistics of the Boolean model for practitioners and mathematicians (1997) · Zbl 0878.62068
[19] Møller, Power diagrams and interaction processes for unions of discs, Adv. Appl. Prob. 40 pp 321– (2008) · Zbl 1146.60322 · doi:10.1239/aap/1214950206
[20] Møller, Likelihood inference for unions of interacting discs, Scand. J. Stat. 37 (3) pp 365– (2010) · Zbl 1226.60016 · doi:10.1111/j.1467-9469.2009.00660.x
[21] Mrkvička, On testing of general random closed set model hypothesis, Kybernetika 45 (2) pp 293– (2009)
[22] Mrkvička, On estimation of intrinsic volume densities of stationary random closed sets, Stoch. Proc. Appl. 118 (2) pp 213– (2008) · Zbl 1148.62023 · doi:10.1016/j.spa.2007.04.004
[23] Nguyen, Integral and differential characterizations Gibbs processes, Math. Nachr. 88 (1) pp 105– (1979) · Zbl 0444.60040 · doi:10.1002/mana.19790880109
[24] Ohser, Statistical analysis of microstructures in materials science (2000) · Zbl 0960.62129
[25] Picard, The multi-scale marked area-interaction point process: a model for the spatial pattern of trees, Scand. J. of Stat. 36 pp 23– (2009) · Zbl 1199.60174
[26] Ripley, Statistical inference for spatial processes (1988) · Zbl 0716.62100 · doi:10.1017/CBO9780511624131
[27] Schmidt, Joint estimators for the specific intrinsic volumes of stationary random sets, Stoch. Proc. Appl. 115 pp 959– (2005) · Zbl 1075.60006 · doi:10.1016/j.spa.2004.12.007
[28] Stoyan, Stochastic geometry and its applications (1995) · Zbl 0838.60002
[29] Takacs, Estimator for the pair-potential of a Gibbsian point process, Math. Operationsforsch. U. Statist., Ser. Statist. 17 pp 428– (1986) · Zbl 0608.62121
[30] Thiedmann, A multiscale approach to the representation of 3D images, with applications to polymer solar cells, Image Anal. Stereology 30 (1) pp 19– (2011) · doi:10.5566/ias.v30.p19-30
[31] Van Lieshout, Proceedings of the International Symposium on Advances in Theory and Applications of Random Sets pp 121– (1997)
[32] Widom, New model for the study of liquid-vapor phase transitions, J. Chem. Phys. 52 pp 1670– (1970) · doi:10.1063/1.1673203
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.