Abstract
We consider the framework in which vectors of variables are observed at different points in a region. Such data are typically characterized by point-wise correlations among the variables, as well as spatial autocorrelation and cross-correlation. To help understand and model this dependence structure, one may define factors which operate at different spatial scales. We consider four such factor-analytic techniques: the linear model of coregionalization (LMC) and three recently proposed alternatives. We apply them to the same set of data, concentrations of major ions in water samples taken from springs in a carbonate mountain aquifer. The methods give quite different results for the spring chemistry, with those of the LMC being much more interpretable. We suggest some possible explanations for this, which may be relevant in other applications as well.
Similar content being viewed by others
References
Bailey TC, Barcellos C, Krzanowski WJ (2005) Use of spatial factors in the analysis of heavy metals in sediments in a Brazilian coastal region. Environmetrics 16:563–572
Bailey TC, Krzanowski WJ (2000) Extensions to spatial factor methods with an illustration in geochemistry. Math Geol 32:657–682
Bailey TC, Krzanowski WJ (2012) An overview of approaches to the analysis and modelling of multivariate geostatistical data. Math Geosc 44:381–393
Bechler A, Romary T, Jeannée, Desnoyers, Y (2013) Geostatistical sampling opimization of contaminated facilities. Stoch Environ Res Risk Assess 27:1967–1974
Clarkson DB (1988a) Remark AS R74. A least squares version of algorithm AS 211: the F-G diagonalization algorithm. Appl Stat 37:317–321
Clarkson DB (1988b) Remark AS R71. A remark on algorithm AS 211: the F-G diagonalization algorithm. Stat Aalgorithms, Appl Stat 37:147–151
da Silva C, Costa J (2014) Minimum/maximum autocorrelation factors applied to grade estimation. Stoch Environ Res Risk Assess 28:1929–1938
Dutilleul P, Pelletier B (2011) Tests of significance for structural correlations in the linear model of coregionalization. Math Geosci 43:819–846
Goovaerts P (1992) Factorial kriging analysis: a useful tool for exploring the structure of multivariate spatial soil information. J Soil Sci 43:597–619
Goovaerts P (1993) Factorial kriging analysis of springwater contents in the Dyle River basin, Belgium. Water Resour Res 29:2115–2125
Goovaerts P (1994a) On a controversial method for modeling a coregionalization. Math Geol 26:197–204
Goovaerts P (1994b) Study of spatial relationships between two sets of variables using multivariate geostatistics. Geoderma 62:93–107
Goulard M, Voltz M (1992) Linear coregionalization model: tools for estimation and choice of cross-varioram matrix. Math Geol 24:269–286
Herut B (1992) The chemical composition and sources of dissolved salts in rainwater in Israel. Ph.D. Thesis, Hebrew University of Jerusalem, 152 pp (in Hebrew)
Howard G, Jahnel J, Frimmel FH, McChesney D, Reed B, Schijven J, Braun-Howland E (2006) Human excreta and sanitation: potential hazards and information needs. Protecting groundwater for health: managing the quality of drinking-water sources. World Health Organization, London, pp 275–308
Ignaccolo R, Mateu J, Giraldo R (2014) Kriging with external drift for functional data for air quality monitoring. Stoch Environ Res Risk Assess 28:1171–1186
Journel AG, Huijbregts ChJ (1978) Mining geostatistics. Academic Press, New York
Krzanowski WJ, Bailey TC (2007) Extraction of spatial features using factor methods illustrated on stream sediment data. Math Geol 39:69–85
Kunsch HR, Papritz A, Bassi F (1997) Generalized cross- covariances and their estimation. Math Geol 29:779–799
Lark RM, Papritz A (2003) Fitting a linear model of coregionalization for soil properties using simulated annealing. Geoderma 115:245–260
Larocque G, Dutilleul P, Pelletier B, Fyles J (2007) Characterization and Quantification of Uncertainty in Coregionalization Analysis. Math Geol 39:263–288
Maestre FT, Rodriguez F, Bautista S, Cortina J, Bellot J (2005) Spatial associations and patterns of perennial vegetation in a semi-arid steppe: a multivariate geostatistics approach. Plant Ecol 179:133–147
Minozzo1, M., and Fruttini, D. (2004) Loglinear spatial factor analysis: an application to diabetes mellitus complications. Environmetrics 15:423–434
Morisette J (1997) Examples using SAS to fit the model of linear coregionalization. Comput Geosci 23:317–323
Oman SD, Vakulenko-Lagun B (2009) Estimation of sill matrices in the linear model of coregionalization. Math Geosci 41:15–27
Pelletier B, Dutilleul P, Larocque G, Fyles JW (2004) Fitting the linear model of coregionalization by generalized least squares. Math Geol 36:323–343
Switzer P, Green A (1984). Min/max autocorrelation factors for multivariate spatial imagery. Technical Report No. 6, Stanford University
Wackernagel H (1989) Description of a computer program for analyzing multivariate spatially distributed data. Comput Geosci 15:593–598
Wackernagel H (1994) Cokriging versus kriging in regionalized multivariate data analysis. Geoderma 62:83–92
Webster R, Atteia O, Dubois JP (1994) Coregionalization of trace metals in the soil in the Swiss Jura. Eur J Soil Sci 45:205–218
Zhang H (2007) Maximum-likelihood estimation for multivariate spatial linear coregionalization models. Environmetrics 18:125–139
Acknowledgments
We would like to thank the reviewers for their very helpful comments.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Oman, S.D., Vakulenko-Lagun, B. & Zilberbrand, M. Methods for descriptive factor analysis of multivariate geostatistical data: a case-study comparison. Stoch Environ Res Risk Assess 29, 1103–1116 (2015). https://doi.org/10.1007/s00477-014-1002-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-014-1002-4