Abstract
With the advancement of technology, data are often recorded continuously and instantaneously. Since the early nineties, this kind of observations have been described by models for functional data. Usually a large set of records for each individual in the sample become in a curve (by using some smoothing method) which is considered as a realization of a random function. In functional regression models these curves are used to establish whether there is a relation with an scalar response (functional regression model with scalar response). If two or more sets of curves are obtained for each individual, more complex functional regression models can be established. In particular, in geosciences, where spatial statistics is a primary tool, functional regression is becoming more frequent. Therefore, it is of interest to develop methodologies for spatially correlated functional data. Also in geosciences, as well as in other areas, it is common that the response variables follow positive skew distributions (for example, those obtained in studies about the level of chemical elements in soil or air). Hence, the standard geostatistical assumption of Gaussian errors, or at least of symmetry, is inappropriate. This type of variables, in non-spatial contexts, have been successfully described by the Birnbaum–Saunders distribution, becoming its modeling a very active research field. However, the use of this distribution in the treatment of geostatistical data has only been applied under stationarity. This paper develops a Birnbaum–Saunders model for geostatistical data considering a non-stationary process using functional covariates. The corresponding parameters are estimated by maximum likelihood and their performance is evaluated through Monte Carlo simulations. We illustrate the proposed model with two geo-referenced data sets, which shows its potential applications and a better performance in relation to the Gaussian model.
Similar content being viewed by others
References
Balakrishnan N, Leiva V, Sanhueza A, Cabrera E (2009) Mixture inverse Gaussian distribution and its transformations, moments and applications. Statistics 43:91–104
Boyhan G (2013) Agricultural statistical data using stata. CRC Press, Boca Raton
Cardot H, Ferraty F, Sarda P (1999) Functional linear model. Stat Probab Lett 45:11–22
Carranza E (2009) Geochemical anomaly and mineral prospectivity mapping in GIS. Elsevier, Oxford
Clarkson D, Fraley C, Gu C, Ramsay J (2005) S+ functional data analysis: user’s manual for windows. Springer, New York
Cuevas A, Febrero M, Fraiman R (2004) An ANOVA test for functional data. Comput Stat Data Anal 47:111–122
de Oliveira V, Kedem B, Short D (1997) Bayesian prediction of transformed Gaussian random fields. J Am Stat Assoc 92:1422–1433
Delicado P (2007) Functional k-sample problem when data are density functions. Comput Stat 22:391–410
Diggle PJ, Ribeiro PJ (2007) Model-based geoestatistics. Springer, New York
Escabias M, Aguilera A, Valderrama M (2004) Principal components estimation of functional logistic regression: discussion of two different approaches. J Nonparametr Stat 16:365–384
Febrero-Bande M, de La Fuente O (2014) Functional regression models with temporal and/or spatial dependence. In: Bongiorno EG, Salinelli E, Goia A, Vieu P (eds) Contributions in infinite-dimensional statistics and related topics, vol 19. Società Editrice Esculapio, Bologna, pp 107–110
Ferraty F, Vieu P (2003) Curves discrimination: a nonparametric functional approaches. Comput Stat Data Anal 44:161–173
Ferraty F, Vieu P (2006) Nonparametric functional data analysis: theory and practice. Springer, New York
Ferreira M, Gomes MI, Leiva V (2012) On an extreme value version of the Birnbaum–Saunders distribution. REVSTAT Stat J 10:181–210
Fillela I, Penuelas J (1994) The red edge position and shape as indicator of plant chlorophyll content, biomass and hydric status. J Remote Sens 15:1459–1470
Galindo J (2004) Development of an explanatory model of the growth and production of pea based on edaphic-environmental variables. Ph.D. Thesis. Universidad Nacional de Colombia, Colombia (in Spanish)
Garcia-Papani F, Leiva V, Uribe-Opazo MA, Aykroyd RG (2018a) Birnbaum–Saunders spatial regression models: diagnostics and application to chemical data. Chemom Intel Lab Syst 177:114–128
Garcia-Papani F, Uribe-Opazo MA, Leiva V, Aykroyd RG (2017) Birnbaum–Saunders spatial modelling and diagnostics applied to agricultural engineering data. Stoch Environ Res Risk Assess 31:105–124
Garcia-Papani F, Leiva V, Ruggeri F, Uribe-Opazo MA (2018b) Kriging with external drift in a Birnbaum–Saunders geostatistical model. Stoch Environ Res Risk Assess 32:1517–1530
Giraldo R, Delicado P, Mateu J (2011) Ordinary kriging for function value spatial data. Environ Ecol Stat 18:411–426
Giraldo R, Molina A, Torres-Leon JL, Acosta M, Martinez S (2016) Study of the spectral signatures of oil palms affected with letal wilt, using functional data analysis. Palmas 39:131–139
Graler B (2014) Modelling skewed spatial random fields through the spatial vine copula. Comput Stat Data Anal 10:87–102
Helsel D, Lee L (2005) Statistical analysis of water-quality data containing multiple detection limits: S-language software for regression on order statistics. Comput Geosci 31:1241–1248
Huang S, Qu Y (2006) The loss in power when the test of differential expression is performed under a wrong scale. J Comput Biol 13:786–797
Huerta M, Leiva V, Liu S, Rodriguez M, Villegas D (2019) On a partial least squares regression model for asymmetric data with a chemical application in mining. Chemom Intell Lab Syst 190:55–68
Johnson NL, Kotz S, Balakrishnan N (1995) Continuous univariate distributions, vol 2. Wiley, New York
Keirstead J (2012) Gaussian process regression with R. http://www.jameskeirstead.ca/blog/gaussian-process-regression-with-r/. Accessed June 2018
Kokoszka P, Reimherr M (2019) Some recent developments in inference for geostatistical functional data. Revista Colombiana de Estadística 42:101–122
Kundu D, Balakrishnan N, Jamalizadeh A (2010) Bivariate Birnbaum–Saunders distribution and associate inference. J Multivar Anal 101:113–125
Lange K (2001) Numerical analysis for statisticians. Springer, New York
Leiva V (2016) The Birnbaum–Saunders distribution. Academic Press, New York
Leiva V, Marchant C, Ruggeri F, Saulo H (2015) A criterion for environmental assessment using Birnbaum–Saunders attribute control charts. Environmetrics 2:463–476
Leurgans S, Moyeed R, Silverman B (1993) Canonical correlation analysis when the data are curves. J R Stat Soc B 55:725–740
Malfait N, Ramsay J (2003) The historical functional linear model. Can J Stat 31:115–128
Marchant C, Leiva V, Cysneiros FJA (2016a) A multivariate log-linear model for Birnbaum–Saunders distributions. IEEE Trans Reliab 65:816–827
Marchant C, Leiva V, Cysneiros FJA, Vivanco JF (2016b) Diagnostics in multivariate generalized Birnbaum–Saunders regression models. J Appl Stat 43:2829–2849
Marchant C, Leiva V, Cysneiros FJA, Liu S (2018) Robust multivariate control charts based on Birnbaum–Saunders distributions. J Stat Comput Simul 88:182–202
Marchant C, Leiva V, Christakos G, Cavieres MA (2019) Monitoring urban environmental pollution by bivariate control charts: new methodology and case study in Santiago, Chile. Environmetrics (in press)
Nocedal J, Wright S (1999) Numerical optimization. Springer, New York
Pezulli S, Silverman B (1993) Some properties of smoothed components analysis for functional data. Comput Stat 8:1–16
Quinn G, Keough M (2002) Experimental design and data analysis for biologist. Cambridge University Press, Cambridge
Core Team R (2018) R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna
Ramsay J, Silverman B (2005) Functional data analysis. Springer, New York
Rasmussen J, Williams C (2006) Gaussian processes for machine learning. MIT Press, Cambridge
Reimman C, Filzmoser P, Garrett R, Dutter R (2008) Statistical data analysis explained: applied environmental statistics with R. Wiley, New York
Renard P, Demougeot-Renard H, Froidevaux R (2005) Geostatistics for environmental application. Springer, New York
Ribeiro P, Diggle P (2015) geoR: analysis of geostatistical data. R package version 1(7–5):1
Rieck JR, Nedelman JR (1991) A log-linear model for the Birnbaum–Saunders distribution. Technometrics 3:51–60
Rimstad K, Omre H (2014) Skew–Gaussian random fields. Spat Stat 10:43–62
Saulo H, Leiva V, Ziegelmann F, Marchant C (2013) A nonparametric method for estimating asymmetric densities based on skewed Birnbaum–Saunders distributions applied to environmental data. Stoch Environ Res Risk Assess 27:147–149
Schabenberger O, Gotway C (2005) Statistical methods for spatial data analysis. Chapman and Hall, London
Shen Q, Faraway J (2004) An F test for linear models with functional responses. Stat Sin 14:1239–1257
Silverman B (1995) Incorporating parametric effects into functional principal components. J R Stat Soc 57:673–689
Villegas C, Paula GA, Leiva V (2011) Birnbaum–Saunders mixed models for censored reliability data analysis. IEEE Trans Reliab 60:748–758
Yao F, Muller H, Wang J (2005) Functional linear regression for longitudinal data. Ann Stat 33:2873–2903
Acknowledgements
The authors would like to thank the editors and four reviewers very much for their constructive comments on an earlier version of this manuscript which resulted in this improved version. This research was supported partially by grant “Fondecyt 1160868” from the National Commission for Scientific and Technological Research of the Chilean government.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix 1
Appendix 1
1.1 Score vector
The elements of the \(K_{\beta }\times 1\) score vector given in (13) are detailed as
where \(\text {tr}({\varvec{A}})\) denotes the trace of \({\varvec{A}}\); \({\varvec{W}} = (W_1, \ldots , W_n)^\top\), with \(W_i = \cosh ((y_i-\mu _i)/2)\), for \(i = 1, \ldots , n\); \({\varvec{V}} = (V_1, \ldots , V_n)^\top\) is defined in (12) and \(\mu _i={\varvec{z}}_i^\top {\varvec{\xi }}\), with \({\varvec{z}}_i\) being the ith row of the matrix \({\varvec{Z}}\) defined in (11).
1.2 Information matrix
For the BS functional regression model the Hessian matrix presented in (15) has elements expressed as
In addition, \(\ddot{{\varvec{\ell }}}({\varvec{b}}_j\alpha ) = \ddot{{\varvec{\ell }}}(\alpha {\varvec{b}}_j)\), \(\ddot{{\varvec{\ell }}}(\phi \alpha ) = \ddot{{\varvec{\ell }}}( \alpha \phi )\), \(\ddot{{\varvec{\ell }}}({\varvec{b}}_j\beta _0) = (\ddot{{\varvec{\ell }}}(\beta _0{\varvec{b}}_j))^\top\), \(\ddot{{\varvec{\ell }}}(\phi \beta _0) = \ddot{{\varvec{\ell }}}( \beta _0\phi )\) and \(\ddot{{\varvec{\ell }}}(\phi {\varvec{b}}_j) = \ddot{{\varvec{\ell }}}({\varvec{b}}_j \phi )\).
Therefore, following Garcia-Papani et al. (2018a), the expected Fisher information matrix given in (16), is formed by the elements
Rights and permissions
About this article
Cite this article
Martínez, S., Giraldo, R. & Leiva, V. Birnbaum–Saunders functional regression models for spatial data. Stoch Environ Res Risk Assess 33, 1765–1780 (2019). https://doi.org/10.1007/s00477-019-01708-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-019-01708-9