{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:50:27Z","timestamp":1791323427011,"version":"4.3.1"},"reference-count":52,"publisher":"Institute of Mathematical Statistics","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Ann. Statist."],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"Bayesian model-based spatial clustering methods are widely used for their flexibility in estimating latent clusters with an unknown number of clusters while accounting for spatial proximity. Many existing methods are designed for clustering finite spatial units, limiting their ability to make predictions or may impose restrictive geometric constraints on the shapes of subregions. Furthermore, the posterior clustering consistency theory of spatial clustering models remains largely unexplored in the literature. In this study, we propose a Spatial Domain Random Partition Model (Spat-RPM) and demonstrate its application for spatially clustered regression, which extends spanning tree-based Bayesian spatial clustering by partitioning the spatial domain into disjoint blocks and using spanning tree cuts to induce contiguous domain partitions. Under an infill-domain asymptotic framework, we introduce a new distance metric to study the posterior concentration of domain partitions. We show that Spat-RPM achieves a consistent estimation of domain partitions, including the number of clusters (which may go to infinity), and derive posterior concentration rates for partition, parameter and prediction. We also establish conditions on the hyperparameters to achieve consistency, offering important practical guidance for hyperparameter selection. Finally, we examine the asymptotic properties of our model through simulation studies and apply it to Atlantic Ocean data.<\/jats:p>","DOI":"10.1214\/26-aos2651","type":"journal-article","created":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T12:51:52Z","timestamp":1790945512000},"page":"2432-2454","source":"Crossref","is-referenced-by-count":0,"title":["Consistent Bayesian spatial domain partitioning using predictive spanning tree methods"],"prefix":"10.1214","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7418-483X","authenticated-orcid":false,"given":"Kun","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Statistics, Texas A&M University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyan","family":"Sang","sequence":"additional","affiliation":[{"name":"Department of Statistics, Texas A&M University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"108","reference":[{"key":"13","doi-asserted-by":"publisher","unstructured":"Frieze, A. M.<\/small> (1985). On the value of a random minimum spanning tree problem. Discrete Appl. Math.<\/i> 10<\/b> 47\u201356.","DOI":"10.1016\/0166-218X(85)90058-7"},{"key":"31","doi-asserted-by":"publisher","unstructured":"Miller, J. W.<\/small> and Harrison, M. T.<\/small> (2018). Mixture models with a prior on the number of components. J. Amer. Statist. Assoc.<\/i> 113<\/b> 340\u2013356.","DOI":"10.1080\/01621459.2016.1255636"},{"key":"8","doi-asserted-by":"publisher","unstructured":"Denison, D. G. T.<\/small>, Mallick, B. K.<\/small> and Smith, A. F. M.<\/small> (1998). A Bayesian CART algorithm. Biometrika<\/i> 85<\/b> 363\u2013377.","DOI":"10.1093\/biomet\/85.2.363"},{"key":"20","doi-asserted-by":"publisher","unstructured":"Kim, H.-M.<\/small>, Mallick, B. K.<\/small> and Holmes, C. C.<\/small> (2005). Analyzing nonstationary spatial data using piecewise Gaussian processes. J. Amer. Statist. Assoc.<\/i> 100<\/b> 653\u2013668.","DOI":"10.1198\/016214504000002014"},{"key":"11","doi-asserted-by":"publisher","unstructured":"FRALEY, C.<\/small> and RAFTERY, A. E.<\/small> (2002). Model-based clustering, discriminant analysis, and density estimation. J. Amer. Statist. Assoc.<\/i> 97<\/b> 611\u2013631.","DOI":"10.1198\/016214502760047131"},{"key":"1","doi-asserted-by":"publisher","unstructured":"ALDOUS, D. J.<\/small> (1990). The random walk construction of uniform spanning trees and uniform labelled trees. SIAM J. Discrete Math.<\/i> 3<\/b> 450\u2013465.","DOI":"10.1137\/0403039"},{"key":"21","doi-asserted-by":"crossref","unstructured":"KNORR-HELD, L.<\/small> and RASSER, G.<\/small> (2000). Bayesian detection of clusters and discontinuities in disease maps. Biometrics<\/i> 56<\/b> 13\u201321.","DOI":"10.1111\/j.0006-341X.2000.00013.x"},{"key":"12","doi-asserted-by":"publisher","unstructured":"Frick, K.<\/small>, Munk, A.<\/small> and Sieling, H.<\/small> (2014). Multiscale change point inference. J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> 76<\/b> 495\u2013580. With 32 discussions by 47 authors and a rejoinder by the authors.","DOI":"10.1111\/rssb.12047"},{"key":"7","doi-asserted-by":"crossref","unstructured":"DASGUPTA, A.<\/small> and RAFTERY, A. E.<\/small> (1998). Detecting features in spatial point processes with clutter via model-based clustering. J. Amer. Statist. Assoc.<\/i> 93<\/b> 294\u2013302.","DOI":"10.1080\/01621459.1998.10474110"},{"key":"49","doi-asserted-by":"publisher","unstructured":"YU, S.<\/small>, WANG, G.<\/small>, WANG, L.<\/small>, LIU, C.<\/small> and YANG, L.<\/small> (2020). Estimation and inference for generalized geoadditive models. J. Amer. Statist. Assoc.<\/i> 115<\/b> 761\u2013774.","DOI":"10.1080\/01621459.2019.1574584"},{"key":"16","doi-asserted-by":"publisher","unstructured":"GUHA, A.<\/small>, HO, N.<\/small> and NGUYEN, X.<\/small> (2021). On posterior contraction of parameters and interpretability in Bayesian mixture modeling. Bernoulli<\/i> 27<\/b> 2159\u20132188.","DOI":"10.3150\/20-BEJ1275"},{"key":"35","doi-asserted-by":"publisher","unstructured":"PAGE, G. L.<\/small> and QUINTANA, F. A.<\/small> (2016). Spatial product partition models. Bayesian Anal.<\/i> 11<\/b> 265\u2013298.","DOI":"10.1214\/15-BA971"},{"key":"24","doi-asserted-by":"publisher","unstructured":"LI, F.<\/small> and SANG, H.<\/small> (2019). Spatial homogeneity pursuit of regression coefficients for large datasets. J. Amer. Statist. Assoc.<\/i> 114<\/b> 1050\u20131062.","DOI":"10.1080\/01621459.2018.1529595"},{"key":"3","doi-asserted-by":"crossref","unstructured":"BURTON, R.<\/small> and PEMANTLE, R.<\/small> (1993). Local characteristics, entropy and limit theorems for spanning trees and domino tilings via transfer-impedances. Ann. Probab.<\/i> 21<\/b> 1329\u20131371.","DOI":"10.1214\/aop\/1176989121"},{"key":"15","doi-asserted-by":"publisher","unstructured":"Gneiting, T.<\/small> and Raftery, A. E.<\/small> (2007). Strictly proper scoring rules, prediction, and estimation. J. Amer. Statist. Assoc.<\/i> 102<\/b> 359\u2013378.","DOI":"10.1198\/016214506000001437"},{"key":"39","doi-asserted-by":"publisher","unstructured":"Schramm, O.<\/small> (2000). Scaling limits of loop-erased random walks and uniform spanning trees. Israel J. Math.<\/i> 118<\/b> 221\u2013288.","DOI":"10.1007\/BF02803524"},{"key":"26","doi-asserted-by":"publisher","unstructured":"Lloyd, S. P.<\/small> (1982). Least squares quantization in PCM. IEEE Trans. Inf. Theory<\/i> 28<\/b> 129\u2013137.","DOI":"10.1109\/TIT.1982.1056489"},{"key":"33","doi-asserted-by":"publisher","unstructured":"Nguyen, X.<\/small> (2013). Convergence of latent mixing measures in finite and infinite mixture models. Ann. Statist.<\/i> 41<\/b> 370\u2013400.","DOI":"10.1214\/12-AOS1065"},{"key":"2","doi-asserted-by":"publisher","unstructured":"ASCOLANI, F.<\/small>, LIJOI, A.<\/small>, REBAUDO, G.<\/small> and ZANELLA, G.<\/small> (2023). Clustering consistency with Dirichlet process mixtures. Biometrika<\/i> 110<\/b> 551\u2013558.","DOI":"10.1093\/biomet\/asac051"},{"key":"46","doi-asserted-by":"publisher","unstructured":"WENDLAND, H.<\/small> (2004). Scattered Data Approximation<\/i>. Cambridge Monographs on Applied and Computational Mathematics<\/i> 17<\/b>. Cambridge Univ. Press, Cambridge.","DOI":"10.1017\/cbo9780511617539"},{"key":"45","unstructured":"WATANABE, S.<\/small> and OPPER, M.<\/small> (2010). Asymptotic equivalence of Bayes cross validation and widely applicable information criterion in singular learning theory. J. Mach. Learn. Res.<\/i> 11<\/b> 3571\u20133594."},{"key":"29","doi-asserted-by":"publisher","unstructured":"LUO, Z. T.<\/small>, SANG, H.<\/small> and MALLICK, B.<\/small> (2024). A nonstationary soft partitioned Gaussian process model via random spanning trees. J. Amer. Statist. Assoc.<\/i> 119<\/b> 2105\u20132116.","DOI":"10.1080\/01621459.2023.2249642"},{"key":"38","doi-asserted-by":"publisher","unstructured":"QUINTANA, F. A.<\/small>, M\u00dcLLER, P.<\/small>, JARA, A.<\/small> and MACEACHERN, S. N.<\/small> (2022). The dependent Dirichlet process and related models. Statist. Sci.<\/i> 37<\/b> 24\u201341.","DOI":"10.1214\/20-sts819"},{"key":"17","doi-asserted-by":"publisher","unstructured":"HU, G.<\/small>, GENG, J.<\/small>, XUE, Y.<\/small> and SANG, H.<\/small> (2023). Bayesian spatial homogeneity pursuit of functional data: An application to the U.S. income distribution. Bayesian Anal.<\/i> 18<\/b> 579\u2013605.","DOI":"10.1214\/22-ba1320"},{"key":"30","unstructured":"MAYNARD, K. R.<\/small>, COLLADO-TORRES, L.<\/small>, WEBER, L. M.<\/small>, UYTINGCO, C.<\/small>, BARRY, B. K.<\/small>, WILLIAMS, S. R.<\/small>, CATALLINI, J. L.<\/small>, TRAN, M. N.<\/small>, BESICH, Z.<\/small> et al. (2021). Transcriptome-scale spatial gene expression in the human dorsolateral prefrontal cortex. Nat. Neurosci.<\/i> 24<\/b> 425\u2013436."},{"key":"4","doi-asserted-by":"crossref","unstructured":"CADEZ, I. V.<\/small>, GAFFNEY, S.<\/small> and SMYTH, P.<\/small> (2000). A general probabilistic framework for clustering individuals and objects. In Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining<\/i> 140\u2013149.","DOI":"10.1145\/347090.347119"},{"key":"5","doi-asserted-by":"publisher","unstructured":"CALI\u0143SKI, T.<\/small> and HARABASZ, J.<\/small> (1974). A dendrite method for cluster analysis. Comm. Statist. Theory Methods<\/i> 3<\/b> 1\u201327.","DOI":"10.1080\/03610927408827101"},{"key":"6","doi-asserted-by":"publisher","unstructured":"DAHL, D. B.<\/small>, JOHNSON, D. J.<\/small> and M\u00dcLLER, P.<\/small> (2022). Search algorithms and loss functions for Bayesian clustering. J. Comput. Graph. Statist.<\/i> 31<\/b> 1189\u20131201.","DOI":"10.1080\/10618600.2022.2069779"},{"key":"9","doi-asserted-by":"crossref","unstructured":"DOBRIN, R.<\/small> and DUXBURY, P.<\/small> (2001). Minimum spanning trees on random networks. Phys. Rev. Lett.<\/i> 86<\/b> 5076.","DOI":"10.1103\/PhysRevLett.86.5076"},{"key":"10","doi-asserted-by":"publisher","unstructured":"FENG, W.<\/small>, LIM, C. Y.<\/small>, MAITI, T.<\/small> and ZHANG, Z.<\/small> (2016). Spatial regression and estimation of disease risks: A clustering-based approach. Stat. Anal. Data Min.<\/i> 9<\/b> 417\u2013434.","DOI":"10.1002\/sam.11314"},{"key":"14","doi-asserted-by":"publisher","unstructured":"GNEDIN, A.<\/small> and PITMAN, J.<\/small> (2006). Exchangeable Gibbs partitions and Stirling triangles. Zap. Nauchn. Sem. S.-Peterburg. Otdel. Mat. Inst. Steklov<\/i>. (POMI<\/i>) 138<\/b> 5674\u20135685.","DOI":"10.1007\/s10958-006-0335-z"},{"key":"18","doi-asserted-by":"publisher","unstructured":"HUANG, K.<\/small>, CHEN, X.<\/small>, GUAN, Y.<\/small> and LI, Y.<\/small> (2025). Partially linear single-index models and functional principal component analysis of spatially and temporally indexed point processes. J. Bus. Econom. Statist.<\/i> 43<\/b> 1077\u20131091.","DOI":"10.1080\/07350015.2025.2475950"},{"key":"19","doi-asserted-by":"crossref","unstructured":"HUANG, K.<\/small> and SANG, H.<\/small> (2026). Supplement to \u201cConsistent Bayesian spatial domain partitioning using predictive spanning tree methods.\u201d https:\/\/doi.org\/10.1214\/26-AOS2651SUPP<\/a>","DOI":"10.1214\/26-AOS2651SUPP"},{"key":"22","unstructured":"LEE, C.<\/small>, LUO, Z. T.<\/small> and SANG, H.<\/small> (2021). T-LoHo: A Bayesian regularization model for structured sparsity and smoothness on graphs. Adv. Neural Inf. Process. Syst.<\/i> 34<\/b> 598\u2013609."},{"key":"23","doi-asserted-by":"publisher","unstructured":"LEE, J.<\/small>, GANGNON, R. E.<\/small> and ZHU, J.<\/small> (2017). Cluster detection of spatial regression coefficients. Stat. Med.<\/i> 36<\/b> 1118\u20131133.","DOI":"10.1002\/sim.7172"},{"key":"25","doi-asserted-by":"publisher","unstructured":"LIAN, H.<\/small> (2010). Posterior convergence and model estimation in Bayesian change-point problems. Electron. J. Stat.<\/i> 4<\/b> 239\u2013253.","DOI":"10.1214\/09-EJS477"},{"key":"27","unstructured":"LUO, Z. T.<\/small>, SANG, H.<\/small> and MALLICK, B.<\/small> (2021). A Bayesian contiguous partitioning method for learning clustered latent variables. J. Mach. Learn. Res.<\/i> 22<\/b> Paper No. 37, 52."},{"key":"28","unstructured":"LUO, Z. T.<\/small>, SANG, H.<\/small> and MALLICK, B.<\/small> (2021). BAST: Bayesian additive regression spanning trees for complex constrained domain. Adv. Neural Inf. Process. Syst.<\/i> 34<\/b> 90\u2013102."},{"key":"32","doi-asserted-by":"publisher","unstructured":"MU, J.<\/small>, WANG, G.<\/small> and WANG, L.<\/small> (2020). Spatial autoregressive partially linear varying coefficient models. J. Nonparametr. Stat.<\/i> 32<\/b> 428\u2013451.","DOI":"10.1080\/10485252.2020.1759596"},{"key":"34","doi-asserted-by":"publisher","unstructured":"PACI, L.<\/small> and FINAZZI, F.<\/small> (2018). Dynamic model-based clustering for spatio-temporal data. Stat. Comput.<\/i> 28<\/b> 359\u2013374.","DOI":"10.1007\/s11222-017-9735-9"},{"key":"36","doi-asserted-by":"publisher","unstructured":"PAN, T.<\/small>, HU, G.<\/small> and SHEN, W.<\/small> (2023). Identifying latent groups in spatial panel data using a Markov random field constrained product partition model. Statist. Sinica<\/i> 33<\/b> 2281\u20132304.","DOI":"10.5705\/ss.202021.0247"},{"key":"40","doi-asserted-by":"publisher","unstructured":"SUGASAWA, S.<\/small> and MURAKAMI, D.<\/small> (2021). Spatially clustered regression. Spat. Stat.<\/i> 44<\/b> Paper No. 100525, 16.","DOI":"10.1016\/j.spasta.2021.100525"},{"key":"41","doi-asserted-by":"crossref","unstructured":"TALLEY, L. D.<\/small> (2011). Descriptive Physical Oceanography<\/i>: An Introduction<\/i>. Academic Press, San Diego.","DOI":"10.1016\/B978-0-7506-4552-2.10001-0"},{"key":"42","doi-asserted-by":"crossref","unstructured":"TEIXEIRA, L. V.<\/small>, ASSUNCAO, R. M.<\/small> and LOSCHI, R. H.<\/small> (2015). A generative spatial clustering model for random data through spanning trees. In 2015 IEEE International Conference on Data Mining<\/i> 997\u20131002. IEEE.","DOI":"10.1109\/ICDM.2015.106"},{"key":"43","unstructured":"TEIXEIRA, L. V.<\/small>, ASSUN\u00c7\u00c3O, R. M.<\/small> and LOSCHI, R. H.<\/small> (2019). Bayesian space-time partitioning by sampling and pruning spanning trees. J. Mach. Learn. Res.<\/i> 20<\/b> Paper No. 85, 35."},{"key":"44","unstructured":"VAN DONGEN, S.<\/small> (2000). Performance criteria for graph clustering and Markov cluster experiments. Rep.-Inf. Syst.<\/i> 12<\/b> 1\u201336."},{"key":"47","unstructured":"WILLETT, R.<\/small>, NOWAK, R.<\/small> and CASTRO, R.<\/small> (2005). Faster rates in regression via active learning. Adv. Neural Inf. Process. Syst.<\/i> 18<\/b>."},{"key":"48","doi-asserted-by":"publisher","unstructured":"YU, S.<\/small>, WANG, G.<\/small> and WANG, L.<\/small> (2025). Distributed heterogeneity learning for generalized partially linear models with spatially varying coefficients. J. Amer. Statist. Assoc.<\/i> 120<\/b> 779\u2013793.","DOI":"10.1080\/01621459.2024.2359131"},{"key":"50","unstructured":"ZENG, C.<\/small>, MILLER, J. W.<\/small> and DUAN, L. L.<\/small> (2023). Consistent model-based clustering using the quasi-Bernoulli stick-breaking process. J. Mach. Learn. Res.<\/i> 24<\/b> Paper No. [153], 32."},{"key":"51","unstructured":"ZHENG, Y.<\/small>, DUAN, L. L.<\/small> and ROY, A.<\/small> (2024). Consistency of graphical model-based clustering: Robust clustering using Bayesian spanning forest. arXiv preprint. Available at arXiv:2409.19129<\/a>."},{"key":"52","doi-asserted-by":"publisher","unstructured":"ZHONG, Y.<\/small>, SANG, H.<\/small>, COOK, S. J.<\/small> and KELLSTEDT, P. M.<\/small> (2023). Sparse spatially clustered coefficient model via adaptive regularization. Comput. Statist. Data Anal.<\/i> 177<\/b> Paper No. 107581, 16.","DOI":"10.1016\/j.csda.2022.107581"},{"key":"37","doi-asserted-by":"publisher","unstructured":"PRIM, R. C.<\/small> (1957). Shortest connection networks and some generalizations. Bell Syst. Tech. J.<\/i> 36<\/b> 1389\u20131401.","DOI":"10.1002\/j.1538-7305.1957.tb01515.x"}],"container-title":["The Annals of Statistics"],"original-title":[],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:05:41Z","timestamp":1791320741000},"score":1,"resource":{"primary":{"URL":"https:\/\/projecteuclid.org\/journals\/annals-of-statistics\/volume-54\/issue-5\/Consistent-Bayesian-spatial-domain-partitioning-using-predictive-spanning-tree-methods\/10.1214\/26-AOS2651.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":52,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1214\/26-aos2651","relation":{},"ISSN":["0090-5364","2168-8966"],"issn-type":[{"value":"0090-5364","type":"print"},{"value":"2168-8966","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]}}}