Space and Space-Time Modeling using Process Convolutions

  • Dave Higdon

Abstract

A continuous spatial model can be constructed by convolving a very simple, perhaps independent, process with a kernel or point spread function. This approach for constructing a spatial process offers a number of advantages over specification through a spatial covariogram. In particular, this process convolution specification leads to computational simplifications and easily extends beyond simple stationary models. This paper uses process convolution models to build space and space-time models that are flexible and able to accommodate large amounts of data. Data from environmental monitoring is considered.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Barry, R. P. & Ver Hoef, J. M. (1996). Blackbox kriging: spatial prediction without specifying variogram models. Journal of Agricultural, Biological, and Environmental Statistics, 1, 297–322.MathSciNetCrossRefGoogle Scholar
  2. Cleveland, W. S. (1979). Robust locally weighted regression and smoothing scatterplots. Journal of the American Statistical Association, 74, 829 – 836.MathSciNetMATHCrossRefGoogle Scholar
  3. Cressie, N. A. C. (1991). Statistics for Spatial Data. Wiley-Interscience.MATHGoogle Scholar
  4. Gelfand, A. E. & Ecker, M. D. (1997). Bayesian variogram modeling for an isotropic spatial process. Journal of Agricultural, Biological, and Environmental Statistics, 2, 347 – 369.MathSciNetCrossRefGoogle Scholar
  5. Guttorp, P., Meiring, W. & Sampson, P. D. (1994). A space-time analysis of ground-level ozone data. Environmetrics, 5, 241 – 254.CrossRefGoogle Scholar
  6. Hartvig, N. V. (2001). A stochastic geometry model for fMRI data. Scandinavian Journal of Statistics, to appear.Google Scholar
  7. Higdon, D. M. (1998). A process-convolution approach to modeling temperatures in the north Atlantic Ocean. Journal of Environmental and Ecological Statistics, 5, 173 – 190.CrossRefGoogle Scholar
  8. Higdon, D. M., Swall, J. & Kern, J. C. (1999). Non-stationary spatial modeling. In Bayesian Statistics 6. Proceedings of the Sixth Valencia International Meeting, 761–768. Oxford University Press.Google Scholar
  9. Kern, J. C. (2000). Bayesian Process-Convolution Approaches to Specifying Spatial Dependence Structure, unpublished PhD dissertation, Institute of Statistics & Decision Sciences, Duke University, Durham, USA.Google Scholar
  10. Ickstadt, K. & Wolpert, R. L. (1999). Spatial regression for marked point processes. In Bayesian Statistics 6. Proceedings of the Sixth Valencia International Meeting, 323 – 341.Google Scholar
  11. Littell, R. C., Milliken, G. A., Stroup, W. W. & Wolfinger, R. D. (1996). SAS System for Mixed Models. SAS Institute.Google Scholar
  12. Matérn, B. (1986). Spatial Variation (Second Edition). Springer-Verlag. Google Scholar
  13. Meiring, W., Guttorp, P. & Sampson, P. D. (1998). Space-time estimation of grid-cell hourly ozone levels for assessment of a deterministic model. Environmental and Ecological Statistics, 5, 197 – 222.CrossRefGoogle Scholar
  14. Müller, P. (1999). Simulation based optimal design. In Bayesian Statistics 6. Proceedings of the Sixth Valencia International Meeting, 323–341.Google Scholar
  15. Nychka, D., Wikle, C. & Royle, J. A. (1999). Large spatial prediction problems and nonstationary random fields. Technical report, National Center for Atmospheric Research.Google Scholar
  16. Patterson, H. D. & Thompson, R. (1971). Recovery of inter-block information when block sizes are unequal. Biometrika, 58, 545 – 554.MathSciNetMATHCrossRefGoogle Scholar
  17. Pinheiro, J. & Bates, D. (2000). Mixed Effects models in S and S-plus. New York: Springer.MATHCrossRefGoogle Scholar
  18. Sampson, P. D. & Guttorp, P. (1992). Nonparametric estimation of nonstationary spatial covariance structure. Journal of the American Statistical Association, 87, 108 – 119.CrossRefGoogle Scholar
  19. Stein, M. (1999). Interpolation of Spatial Data: Some Theory for Kriging. New York: Springer-Verlag.MATHCrossRefGoogle Scholar
  20. Stroud, J., Müller, P. & Sanso, B. (1999). Dynamic models for spatio-temporal data. Technical Report 99-20, Institute of Statistics and Decision Sciences, Duke University.Google Scholar
  21. Thiébaux, H. J. (1997). The power of the duality in spatial-temporal estimation. Journal of Climatology, 10, 567 – 573.CrossRefGoogle Scholar
  22. Thiébaux, H. J. & Pedder, M. A. (1987). Spatial Objective Analysis: with applications in atmospheric science. San Diego: Academic Press.Google Scholar
  23. Ver Hoef, J. & Barry, R. P. (1998). Constructing and fitting models for cokriging and multivariable spatial prediction. Journal of Statistical Planning and Inference, 69, 275–294.MathSciNetMATHCrossRefGoogle Scholar
  24. Ver Hoef, J., Cressie, N. & Barry, R. (2000). Flexible spatial models based on the fast Fourier transform (FFT) for cokriging. Technical report, Department of Statistics, The Ohio State University.Google Scholar
  25. von Storch, H. & Zwiers, F. W. (1999). Statistical Analysis in Climate Research. New York: Cambridge University Press.Google Scholar
  26. Wackernagel, H. (1995). Multivariate Geostatistics. An Introduction With Applications. Springer-Verlag.MATHGoogle Scholar
  27. West, M. & Harrison, J. (1997). Bayesian Forecasting and Dynamic Models (Second Edition). New York: Springer-Verlag.Google Scholar
  28. Wolpert, R. L. & Ickstadt, K. (1998). Poisson/gamma random field models for spatial statistics. Biometrika, 85, 251 – 267.MathSciNetMATHCrossRefGoogle Scholar
  29. Yaglom, A. M. (1987). Correlation Theory of Stationary and Related Random Functions. Volume I: Basic Results. Springer-Verlag, New York.MATHGoogle Scholar
  30. Yaglom, A. M. (1987). Correlation Theory of Stationary and Related Random Functions. Volume II: Supplementary Notes and References. Springer- Verlag, New York.MATHGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2002

Authors and Affiliations

  • Dave Higdon
    • 1
  1. 1.Institute of Statistics and Decision SciencesDuke UniversityDurhamUSA

Personalised recommendations