Publicado
2017-12-23

Predicción espacial de un escalar basada en datos de un campo aleatorio funcional

Spatial prediction of a scalar variable based on data of a functional random field

DOI: https://doi.org/10.15332/2422474x.3645

Resumen (es)

Kriging y cokriging y sus versiones relacionadas son ténicas ampliamente conocidas y usadas en análisis de datos espaciales. Sin embargo cuando los datos son curvas se requiere un puente entre análisis de datos funcionales y geoestadística. Aqu´ı se da una revisión sobre el uso de cokriging y de kriging multivariado para el caso en que las observaciones en cada sitio de muestreo corresponden a muestras de funciones aleatorias. Se extiende la geoestad´ıstica multivariada al contexto funcional. El método cokriging propuesto pemite predecir una variable en un periodo de tiempo como en el sentido multivariado, pero considerando como variables auxiliares curvas en vez de vectores. También se muestra como extender el kriging multivariable al caso funcional definiendo un predictor de una curva completa basado en la información de curvas en sitios cercanos. En las dos propuestas se usan m´etodos no param´etricos de suavizado por base de funciones. Se comprueba que las dos aproximaciones considerdas coinciden. Se emplea un modelo lineal de corregionalización (MLC) para definir la dependencia entre los coeficientes resultantes del ajuste de las bases de funciones y por consiguiente para la estimación de los parámetros funcionales. A manera de ilustración la metodología propuesta es aplicada al anáisis de dos conjuntos de datos reales correspondientes por una lado a temperaturas diarias medidas en 35 estaciones meteorológicas de las provincias mar´ıtimas de Canada y por el otro a datos de resitencia mecánica a la penetración colectados en 32 puntos de muestreo en una parcela experimental.

Palabras clave (es): Base de funciones, cokriging multivariado, modelo lineal de corregionalización, modelo lineal funcional, validación cruzada.

Resumen (en)

Kriging and cokriging and their several related versions are techniques widely known and used in spatial data analysis. However, when the spatial data are functions a bridge between functional data analysis and geostatistics has to be built. I give an overview to cokriging analysis and multivariable spatial prediction to the case where the observations at each sampling location consist of samples of random functions. I extend multivariable geostatistical methods to the functional context. Our cokriging method predicts one variable at a time as in a classical multivariable sense, but considering as auxiliary information curves instead of vectors. I also give an extension of multivariable kriging to the functional context where is defined a predictor of a whole curve based on samples of curves located at a neighborhood of the prediction site. In both cases a non-parametric approach based on basis function expansion is used to estimate the parameters, and I prove that both proposals coincide when using such an approach. A linear model of coregionalization is used to define the spatial dependence among the coefficients of the basis functions, and therefore for estimating the functional parameters. As an illustration the methodological proposals are applied to analyze two real data sets corresponding to average daily temperatures measured at 35 weather stations located in the Canadian Maritime Provinces, and penetration resistance data collected at 32 sampling sites of an experimental plot.

Palabras clave (en): basis functions, Cross-validation, functional linear model, linear model of corregionalization, multivariable cokriging.

Referencias

Bogaert, P. (1996), ‘Comparison of kriging techniques in a space-time context’, Mathematical Geology 28(1), 73–86.

Borgault, G. & Marcotte, D. (1991), ‘The multivariable variogram and its application to the linear coregionalization model’, Mathematical Geology 23(10), 899–928.

Cardot, H., Crambes, C., Kneip, A. & Sarda, P. (2007), ‘Smoothing spline estimators in functional linear regression with errors in variables’, Computational Statistics & Data Analysis 51(10), 4832–4848.

Chan, K., Oates, A., Swan, A., Hayes, R., Dear, B. & Peoples, M. (2006), ‘Agronomic consequences of tractor wheel compaction on a clay soil’, Soil & Tillage Research 89, 13–21.

Cressie, N. (1993), Statistic for spatial data, Jhon Wiley & Sons, New York. Cuevas, A., Febrero, M. & Fraiman, R. (2004), ‘An anova test for functional data.’, Computational Statistics & Data Analysis 47, 111–122.

Ferraty, F. & Vieu, P. (2003), ‘Curves discrimination. A non parametric functional approaches’, Computational Statistics & Data Analysis 44, 161–173.

Ferraty, F. & Vieu, P. (2006), Non parametric functional data analysis. Theory and practice, Springer, New York.

Freddi, O., Carvalho, M., Versonesi, M., Guilherme, J. & Carvalho, J. (2006), ‘Relationship between maize yield and soil mechanical resistance to penetration under conventional tillage’, Engenharia Agr´ıcola 26(1), 113–121.

Galindo, J. (2004), Desarrollo de un modelo explicativo del crecimiento y producción de la arveja en función de variables edáfico-ambientales., PhD thesis, National University of Colombia.

Giraldo, R. (2009), Geostatistical analysis of functional data, PhD thesis, Universitat Politécnica de Catalunya.

Giraldo, R., Delicado, P. & Mateu, J. (2010), ‘Continuous time-varying kriging for spatial prediction of functional data: An environmental application’, Journal of Agricultural, Biological, and Environmental Statistics 15(1), 66–82.

Giraldo, R., Delicado, P. & Mateu, J. (2011), ‘Ordinary kriging for function-valued spatial data’, Environmental and Ecological Statistics 18, 411–426.

González-Manteiga, W. & Vieu, P. (2007), ‘Statistics for functional data’, Computational Statistics and Data Analysis 51, 4788–4792.

Goulard, M. & Voltz, M. (1993), Geostatistical interpolation of curves: A case study in soil science, in A. Soares, ed., ‘Geostatistics Tr´oia ´92’, Vol. 2, Kluwer Academic Press, pp. 805–816.

Hall, P. & Hosseini-Nassab, M. (2006), ‘On properties of functional principal components analysis’, Journal of the Royal Statistical Society, Series B 68, 109–126.

Hollander, T. & Wolfe, D. (1999), Nonparametric Statistical Methods, John Wiley & Sons, New York.

Leiva, F. (2003), ‘Manejo sostenible del suelo bajo la concepción de agriculturade precisión’. Research project partially supported by COLCIENCIAS, Colombia.

Malfait, N. & Ramsay, J. (2003), ‘The historical functional linear model’, The Canadian Journal of Statistics 31(2), 115–128.

Matérn, B. (n.d.), Spatial variation, Springer-Verlag.

Myers, D. (1982), ‘Matrix formulation of Co-kriging’, Mathematical Geology 14(3), 249–257.

Nerini, D., Monestiez, P. & Manté, C. (2010), ‘Cokriging for spatial functionaldata’, Journal of Multivariate Analysis 101, 409–418.

Pebesma, E. (2004), ‘Multivariable geostatistics in S. The gstat package’, Computers & Geosciences 30, 683–691.

R Development Core Team (2005), R: A language and environment for statistical computing, R Foundation for Statistical Computing, Vienna, Austria. ISBN3-900051-07-0, http://www.R-project.org.

Ramsay, J. & Silverman, B. (2005), Functional data analysis. Second edition, Springer,New York.

Stanley, D. (2002), Canada´s Maritime provinces. First edition, Lonely Planet Publications, Marybirnong.

Ver Hoef, J. & Barry, R. (1998), ‘Constructing and fitting models for cokriging and multivariable spatial prediction’, Journal of Statistical Planning and Inference 69, 275–294.

Ver Hoef, J. & Cressie, N. (1993), ‘Multivariable spatial prediction’, Mathematical Geology 25(2), 219–240.

Wackernagel, H. (1995), Multivariable geostatistics:An introduction with applications, Springer-Verlag, Berlin.

Yamanishi, Y. & Tanaka, Y. (2003), ‘Geographically weighted functional multiple regression analysis: A numerical investigation.’, Journal of Japanese Society

of Computational Statistics 15, 307–317.

Dimensions

PlumX

Visitas

689

Descargas

Los datos de descarga aún no están disponibles.

Cómo citar

Ramón, Pedro, & Jorge. (2017). Predicción espacial de un escalar basada en datos de un campo aleatorio funcional. Comunicaciones En Estadística, 10(2), 315-344. https://doi.org/10.15332/2422474x.3645

Artículos más leídos del mismo autor/a