×

Computational issues for perfect simulation in spatial point patterns. (English) Zbl 1035.62097

Summary: Due to model complexity, spatial statistics often rely on simulation methods. Probably the most common such method is Markov chain Monte Carlo (MCMC), which draws approximate samples of the target distribution as the equilibrium distribution of a Markov chain. Perfect simulation methods are MCMC algorithms which ensure that the exact target distribution is sampled. This paper describes perfect simulation methods of locally stable point processes based on coupling from the past algorithms and provides an intensive simulation study analyzing the behaviour of these techniques under a large variety of practical situations.

MSC:

62M30 Inference from spatial processes
65C40 Numerical analysis or methods applied to Markov chains
65C05 Monte Carlo methods
65C60 Computational problems in statistics (MSC2010)
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Propp, J. G.; Wilson, D. B., Exact sampling with coupled Markov chains and applications to statistical mechanics, Random Struct. Algorithms, 9, 1&2, 223-252 (1996) · Zbl 0859.60067
[2] Fill, J. A., An interruptible algorithm for perfect sampling via Markov chains, Ann. Appl. Probab., 8, 1, 131-162 (1998) · Zbl 0939.60084
[3] Thönnes, E., Perfect simulation of some point processes for the impatient user, Adv. Appl. Probab., Stochastic Geometry Statist. Appl., 31, 69-87 (1999) · Zbl 0979.60062
[4] Kendall, W. S., Perfect simulation for the area-interaction point process, (Accardi, L.; Heyde, C. C., Probability towards 2000 (1998), Springer), 218-234 · Zbl 1045.60503
[5] Kendall, W. S.; Møller, J., Perfect simulation using dominating processes on ordered spaces, with application to locally stable point processes, Adv. Appl. Probab., 32, 844-865 (2000) · Zbl 1123.60309
[6] Møller, J., Markov chain Monte Carlo and spatial point processes, (Barndorff Nielsen, O. E.; Kendall, W. S.; van Lieshout, M. N.M., Stochastic geometry: likelihood and computation (1999), Chapman and Hall/CRC: Chapman and Hall/CRC Boca-Raton), 141-172
[7] Berthelsen KK, Møller J, A primer on perfect simulation for spatial point processes, Preprint 2002. Department of Mathematical Sciences, Aalborg University; Berthelsen KK, Møller J, A primer on perfect simulation for spatial point processes, Preprint 2002. Department of Mathematical Sciences, Aalborg University
[8] Møller J. A review on perfect simulation in stochastic geometry. In: Basawa IV, Taylor IV, editors. Selected Proceedings of the Symposium on Inference for Stochastic Processes, vol. 37. IMS Lecture Notes & Monographs Series, 2001. p. 333-55; Møller J. A review on perfect simulation in stochastic geometry. In: Basawa IV, Taylor IV, editors. Selected Proceedings of the Symposium on Inference for Stochastic Processes, vol. 37. IMS Lecture Notes & Monographs Series, 2001. p. 333-55
[9] Berthelsen KK, Møller J. Spatial jump processes and perfect simulation, Preprint, 2001. Department of Mathematical Sciences, Aalborg University; Berthelsen KK, Møller J. Spatial jump processes and perfect simulation, Preprint, 2001. Department of Mathematical Sciences, Aalborg University
[10] Wilson, D. B., How to couple from the past using a read-once source of randomness, Random Struct. Algorithms, 16, 85-113 (2000) · Zbl 0952.60072
[11] Fernández, R.; Ferrari, P. A.; Garcia, N. L., Perfect simulation for interacting point processes, loss networks and Ising models, Stochastic Processes and Applications, 102, 63-88 (2002) · Zbl 1075.60583
[12] Geyer, C. J., Likelihood inference for spatial point processes, (Barndorff Nielsen, O. E.; Kendall, W. S.; van Lieshout, M. N.M., Stochastic geometry: likelihood and computation (1999), Chapman and Hall/CRC: Chapman and Hall/CRC Boca-Raton), 79-140
[13] Strauss, D. J., A model for clustering, Biometrika, 63, 467-475 (1975) · Zbl 0313.62044
[14] Baddeley, A. J.; van Lieshout, M. N.M., Area-interaction point processes, Ann. Inst. Stat. Math., 47, 601-619 (1995) · Zbl 0848.60051
[15] Foss, S. G.; Tweedie, R. L., Perfect simulation and backward coupling, Stochastic Models, 14, 1-2, 187-203 (1998) · Zbl 0934.60088
[16] Kendall, W. S., Perfect simulation for spatial point processes, Bull. Int. Stat. Inst. 1st Session, Istanbul, 3, 163-166 (1997) · Zbl 0923.60051
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.