Biometrika Advance Access originally published online on December 3, 2007
Biometrika 2007 94(4):809-825; doi:10.1093/biomet/asm071
Articles |
Generalized Spatial Dirichlet Process Models
School of Management, Yale University, New Haven, Connecticut 06520-8200, U.S.A. jd522{at}som.yale.edu
Department of Mathematics and Statistics, University of New Mexico, Albuquerque, NM 87131, U.S.A. michele{at}stat.unm.edu
Institute of Statistics and Decision Sciences, Duke University, Durham, North Carolina 27708-0251, U.S.A. alan{at}stat.duke.edu
Received for publication 1 December 2005. Revision received 1 April 2007.
Many models for the study of point-referenced data explicitly introduce spatial random effects to capture residual spatial association. These spatial effects are customarily modelled as a zero-mean stationary Gaussian process. The spatial Dirichlet process introduced by Gelfand et al. (2005) produces a random spatial process which is neither Gaussian nor stationary. Rather, it varies about a process that is assumed to be stationary and Gaussian. The spatial Dirichlet process arises as a probability-weighted collection of random surfaces. This can be limiting for modelling and inferential purposes since it insists that a process realization must be one of these surfaces. We introduce a random distribution for the spatial effects that allows different surface selection at different sites. Moreover, we can specify the model so that the marginal distribution of the effect at each site still comes from a Dirichlet process. The development is offered constructively, providing a multivariate extension of the stick-breaking representation of the weights. We then introduce mixing using this generalized spatial Dirichlet process. We illustrate with a simulated dataset of independent replications and note that we can embed the generalized process within a dynamic model specification to eliminate the independence assumption.
Key Words: Dirichlet process mixing • Dynamic model • Latent process • Non-Gaussian • Nonstationary • Stick breaking
References
-
Agarwal D., Gelfand A. Slice Gibbs sampling for simulation based fitting of spatial data models. Statist. Comp. (2005) 15:61–9.[CrossRef]
Albert J., Chib S. Bayesian analysis of binary and polychotomous response data. J. Am. Statist. Assoc. (1993) 88:669–79.[CrossRef][ISI]
Banerjee S., Gelfand A., Sirmans C. Directional rates of change under spatial process models. J. Am. Statist. Assoc. (2003) 98:946–54.[CrossRef][ISI]
Brown P., Diggle P., Henderson R. A non-Gaussian spatial process model for opacity of flocculated paper. Scand. J. Statist. (2003) 30:355–68.[CrossRef]
Bush C. A., MacEachern S. N. A semiparametric Bayesian model for randomised block designs. Biometrika (1996) 83:275–85.
Cifarelli D., Regazzini E. Problemi statistici non parametrici in condizioni di scambiabilità parziale. Impiego di medie associative. Quad. Istit. Mat. Finanz. Univ. Torino (1978) III:1–13.
Damian D., Sampson P., Guttorp P. Bayesian estimation of semi-parametric non-stationary spatial covariance structures. Environmetrics (2001) 12:161–78.[CrossRef][ISI]
De Iorio M., Müller P., Rosner G., MacEachern S. An ANOVA model for dependent random measures. J. Am. Statist. Assoc. (2004) 99:205–15.[CrossRef][ISI]
Ecker M., Gelfand A. Spatial modeling and prediction under stationary non-geometric range anisotropy. Envir. Ecol. Statist. (2003) 10:165–78.[CrossRef]
Escobar M. D., West M. {B}ayesian density estimation and inference using mixtures. J. Am. Statist. Assoc. (1995) 90:577–88.[CrossRef][ISI]
Ferguson T. S. A Bayesian analysis of some nonparametric problems. Ann. Statist. (1973) 1:209–30.[CrossRef]
Ferguson T. S. Prior distributions on spaces of probability measures. Ann. Statist. (1974) 2:615–29.[CrossRef]
Fernandez C., Green P. Modelling spatially correlated data via mixtures: a {B}ayesian approach. J. R. Statist. Soc. B (2002) 64:805–26.[CrossRef]
Gelfand A. E., Smith A. F. M. Sampling-based approaches to calculating marginal densities. J. Am. Statist. Assoc. (1990) 85:398–409.[CrossRef][ISI]
Gelfand A., Kottas A., MacEachern S. Bayesian nonparametric spatial modeling with Dirichlet processes mixing. J. Am. Statist. Assoc. (2005) 100:1021–35.[CrossRef][ISI]
Griffin J., Steel M. Order-based dependent dirichlet processes. J. Am. Statist. Assoc. (2006) 101:179–94.[CrossRef][ISI]
Higdon D., Swall J., Kern J. Non-stationary spatial modeling. In: Bayesian Statistics 6—Bernardo J. M., Berger J. O., Dawid A. P., Smith A. F. M., eds. (1999) Oxford: Oxford University Press. 761.
Ishwaran H., James L. Gibbs sampling methods for stick breaking priors. J. Am. Statist. Assoc. (2001) 96:161–73.[CrossRef][ISI]
Ishwaran H., Zarepour M. Dirichlet prior sieves in finite normal mixtures. Statist. Sinica (2002) 12:941–63.
Ishwaran H., Zarepour M. Exact and approximate sum-representations for the Dirichlet process. Can. J. Statist. (2002) 30:269–83.[CrossRef]
Kent J. Continuity properties of random fields. Ann. Prob. (1989) 17:1432–40.[CrossRef]
MacEachern S. Estimating normal means with a conjugate style Dirichlet prior. Commun. Statist. B (1994) 23:727–41.
MacEachern S. N., Müller P. Estimating mixture of Dirichlet process models. J. Comp. Graph. Statist. (1998) 7:223–38.[CrossRef]
Palacios M., Steel M. Non-Gaussian Bayesian geostatistical modeling. J. Am. Statist. Assoc. (2006) 101:604–18.[CrossRef][ISI]
Sampson P., Guttorp P. Nonparametric estimation of nonstationary spatial covariance structure. J. Am. Statist. Assoc. (1992) 87:108–19.[CrossRef][ISI]
Schmidt A. M., O'Hagan A. Bayesian inference for nonstationary spatial covariance structure via spatial deformations. J. R. Statist. Soc. B (2003) 65:745–58.
Sethuraman J. A constructive definition of Dirichlet priors. Statist. Sinica (1994) 4:639–50.
CiteULike 
Connotea 
Del.icio.us What's this?
| ||||||||||||||||||||||||||||||||||||||||||||||||||