Advertisement

Composite Likelihood Inference for Multivariate Gaussian Random Fields

  • Moreno BevilacquaEmail author
  • Alfredo Alegria
  • Daira Velandia
  • Emilio Porcu
Article

Abstract

In the recent years, there has been a growing interest in proposing covariance models for multivariate Gaussian random fields. Some of these covariance models are very flexible and can capture both the marginal and the cross-spatial dependence of the components of the associated multivariate Gaussian random field. However, effective estimation methods for these models are somehow unexplored. Maximum likelihood is certainly a useful tool, but it is impractical in all the circumstances where the number of observations is very large. In this work, we consider two possible approaches based on composite likelihood for multivariate covariance model estimation. We illustrate, through simulation experiments, that our methods offer a good balance between statistical efficiency and computational complexity. Asymptotic properties of the proposed estimators are assessed under increasing domain asymptotics. Finally, we apply the method for the analysis of a bivariate dataset on chlorophyll concentration and sea surface temperature in the Chilean coast.

Keywords

Cross-covariance Large datasets Geostatistics 

Notes

Acknowledgments

The research work conducted by Moreno Bevilacqua was supported in part by FONDECYT Grant 11121408, Chile. Emilio Porcu has been supported by FONDECYT Grant 1130647.

Supplementary material

13253_2016_256_MOESM1_ESM.pdf (236 kb)
Supplementary material 1 (pdf 235 KB)

References

  1. Apanasovich, T., Genton, M., and Sun, Y. (2012), “A valid Matérn class of cross-covariance functions for multivariate random fields with any number of components,” Journal of the American Statistical Association, 97, 15–30.MathSciNetzbMATHGoogle Scholar
  2. Bevilacqua, M., Fassò, A., Gaetan, C., Porcu, E., and Velandia, D. (2016), “Covariance tapering for multivariate Gaussian random fields estimation,” Statistical Methods & Applications, 25(1), 21–37.MathSciNetCrossRefzbMATHGoogle Scholar
  3. Bevilacqua, M., and Gaetan, C. (2015), “Comparing composite likelihood methods based on pairs for spatial Gaussian random fields,” Statistics and Computing, 25, 877–892.MathSciNetCrossRefzbMATHGoogle Scholar
  4. Bevilacqua, M., Gaetan, C., Mateu, J., and Porcu, E. (2012), “Estimating space and space-time covariance functions for large data sets: a weighted composite likelihood approach,” Journal of the American Statistical Association, 107, 268–280.MathSciNetCrossRefzbMATHGoogle Scholar
  5. Bevilacqua, M., Vallejos, R., and Velandia, D. (2015), “Assessing the significance of the correlation between the components of a bivariate Gaussian random field,” Environmetrics, 26, 545–556.MathSciNetCrossRefGoogle Scholar
  6. Boyce, D. G., Lewis, M. R., and Worm, B. (2010), “Global phytoplankton decline over the past century,” Nature. International weekly journal of science, 466. doi: 10.1038/nature09268.
  7. Castruccio, S., Huser, R., and Genton, M. G. (2016), “High-order composite likelihood inference for max-stable distributions and processes,” Journal of Computational and Graphical Statistics. To appear.Google Scholar
  8. Daley, D., Porcu, E., and Bevilacqua, M. (2015), “Classes of compactly supported covariance functions for multi- variate random fields,” Stoch Environ Res Risk Assess, 29, 1249–1263.CrossRefGoogle Scholar
  9. Davis, R., and Yau, C.-Y. (2011), “Comments on pairwise likelihood in time series models,” Statistica Sinica, 21, 255–277.MathSciNetzbMATHGoogle Scholar
  10. Doney, S. C., Ruckelshaus, M., Duffy, J. E., Barry, J. P., Chan, F., English, C. A., Galindo, H. M., Grebmeier, J. M., Hollowed, A. B., Knowlton, N., Polovina, J., Rabalais, N. N., Sydeman, W. J., and Talley, L. D. (2012), “Annual Review of Marine Science,” Nature. International weekly journal of science, 4, 11–37.Google Scholar
  11. Eidsvik, J., Shaby, B., Reich, B., Wheeler, M., and Niemi, J. (2014), “Estimation and prediction in spatial models with block composite likelihoods,” Journal of Computational and Graphical Statistics, 29, 295–315.MathSciNetCrossRefGoogle Scholar
  12. Furrer, R., Bachoc, F., and Du, J. (2016), “Asymptotic properties of multivariate tapering for estimation and prediction,” Journal of Multivariate Analysis, In press.Google Scholar
  13. Furrer, R., Genton, M. G., and Nychka, D. (2006), “Covariance tapering for interpolation of large spatial datasets,” Journal of Computational and Graphical Statistics, 15, 502–523.MathSciNetCrossRefGoogle Scholar
  14. Genton, M. G., Padoan, S., and Sang, H. (2015), “Multivariate max-stable spatial processes,” Biometrika, 102, 215 –230.MathSciNetCrossRefzbMATHGoogle Scholar
  15. Genton, M., and Kleiber, W. (2015), “Cross-Covariance Functions for Multivariate Geostatistics,” Statistical Science, in press.Google Scholar
  16. Gneiting, T. (2002), “Compactly supported correlation functions,” Journal of Multivariate Analysis, 83, 493–508.MathSciNetCrossRefzbMATHGoogle Scholar
  17. Gneiting, T., Genton, M. G., and Guttorp, P. (2007), “Geostatistical space-time models, stationarity, separability and full symmetry,” in Statistical Methods for Spatio-Temporal Systems, eds. B. Finkenstadt, L. Held, and V. Isham, Boca Raton: FL: Chapman & Hall/CRC, pp. 151–175.Google Scholar
  18. Gneiting, T., Kleiber, W., and Schlather, M. (2010), “Matérn Cross-Covariance Functions for Multivariate Random Fields,” Journal of the American Statistical Association, 105, 1167–1177.MathSciNetCrossRefzbMATHGoogle Scholar
  19. Goulard, M., and Voltz, M. (1992), “Linear coregionalization model: Tools for estimation and choice of cross-variogram matrix,” Mathematical Geology, 24, 269–286.CrossRefGoogle Scholar
  20. Heagerty, P., and Lumley, T. (2000), “Window subsampling of estimating functions with application to regression models,” Journal of the American Statistical Association, 95, 197–211.MathSciNetCrossRefzbMATHGoogle Scholar
  21. Joe, H., and Lee, Y. (2009), “On weighting of bivariate margins in pairwise likelihood,” Journal of Multivariate Analysis, 100, 670–685.MathSciNetCrossRefzbMATHGoogle Scholar
  22. Kaufman, C. G., Schervish, M. J., and Nychka, D. W. (2008), “Covariance tapering for likelihood-based estimation in large spatial data sets,” Journal of the American Statistical Association, 103, 1545–1555.MathSciNetCrossRefzbMATHGoogle Scholar
  23. Lee, A., Yau, C., Giles, M., Doucet, A., and Holmes, C. (2010), “On the utility of graphics cards to perform massively parallel simulation of advanced Monte Carlo methods,” Journal of Computational and Graphical Statistics, 19, 769 –789.CrossRefGoogle Scholar
  24. Lee, Y., and Lahiri, S. (2002), “Least squares variogram fitting by spatial subsampling,” Journal of the Royal Statistical Society B, 64, 837–854.MathSciNetCrossRefzbMATHGoogle Scholar
  25. Li, B., and Zhang, H. (2011), “An approach to modeling asymmetric multivariate spatial covariance structures,” Journal of Multivariate Analysis, 102, 1445–1453.MathSciNetCrossRefzbMATHGoogle Scholar
  26. Lindsay, B. (1988), “Composite likelihood methods,” Contemporary Mathematics, 80, 221–239.MathSciNetCrossRefzbMATHGoogle Scholar
  27. Padoan, S. A., and Bevilacqua, M. (2015), “Analysis of Random Fields Using CompRandFld,” Journal of Statistical Software, 63, 1–27.CrossRefGoogle Scholar
  28. Pelletier, B., Dutilleul, P., Larocque, G., and Fyles, J. (2004), “Fitting the linear model of coregionalization by generalized least squares,” Mathematical Geology, 36(3), 323–343.CrossRefzbMATHGoogle Scholar
  29. Porcu, E., Daley, D., Buhmann, M., and Bevilacqua, M. (2013), “Radial basis functions with compact support for multivariate geostatistics,” Stochastic Environmental Research and Risk Assessment, 27, 909–922.CrossRefGoogle Scholar
  30. Shaby, B., and Ruppert, D. (2012), “Tapered covariance: Bayesian estimation and asymptotics,” Journal of Computational and Graphical Statistics, 21, 433–452.MathSciNetCrossRefGoogle Scholar
  31. Stein, M. (2005), “Space-time covariance functions,” Journal of the American Statistical Association, 100, 310–321.MathSciNetCrossRefzbMATHGoogle Scholar
  32. Stein, M., Chi, Z., and Welty, L. (2004), “Approximating likelihoods for large spatial data sets,” Journal of the Royal Statistical Society B, 66, 275–296.MathSciNetCrossRefzbMATHGoogle Scholar
  33. Suchard, M., Wang, Q., anf J. Frelinger, C. C., Cron, A., and West, M. (2010), “Understanding GPU programming for statistical computation: studies in massively parallel massive mixtures,” Journal of Computational and Graphical Statistics, 19, 419 –438.MathSciNetCrossRefGoogle Scholar
  34. Varin, C., Reid, N., and Firth, D. (2011), “An overview of composite likelihood methods,” Statistica Sinica, 21, 5–42.MathSciNetzbMATHGoogle Scholar
  35. Varin, C., and Vidoni, P. (2005), “A note on composite likelihood inference and model selection,” Biometrika, 52, 519–528.MathSciNetCrossRefzbMATHGoogle Scholar
  36. Wackernagel, H. (2003), Multivariate Geostatistics: An Introduction with Applications, 3rd edn, New York: Springer.CrossRefzbMATHGoogle Scholar
  37. Wood, S. (2006), Generalized Additive Models: An Introduction with R, : Chapman and Hall CRC.zbMATHGoogle Scholar
  38. Zhang, H. (2007), “Maximum-likelihood estimation for multivariate spatial linear coregionalization models,” Environmetrics, 18, 125–139.MathSciNetCrossRefGoogle Scholar

Copyright information

© International Biometric Society 2016

Authors and Affiliations

  • Moreno Bevilacqua
    • 1
    Email author
  • Alfredo Alegria
    • 2
  • Daira Velandia
    • 1
    • 3
  • Emilio Porcu
    • 2
  1. 1. Instituto de EstadísticaUniversidad de ValparaísoValparaísoChile
  2. 2. Departamento de MatemáticaUniversidad Técnica Federico Santa MaríaValparaísoChile
  3. 3. Facultad de Ciencias BásicasUniversidad Tecnológica de BolívarCartagenaColombia

Personalised recommendations