Abstract
In oceanography, modeling wave fields requires the use of statistical tools capable of handling the circular nature of the data measurements. An important issue in ocean wave analysis is the study of height and direction waves, being direction values recorded as angles or, equivalently, as points on a unit circle. Hence, reconstruction of a wave direction field on the sea surface can be approached by the use of a linear–circular regression model, viewing wave directions as a realization of a circular spatial process whose trend should be estimated. In this paper, we consider a spatial regression model with a circular response and several real-valued predictors. Nonparametric estimators of the circular trend surface are proposed, accounting for the (unknown) spatial correlation. Some asymptotic results about these estimators as well as some guidelines for their practical implementation are also given. The performance of the proposed estimators is investigated in a simulation study. An application to wave directions in the Adriatic Sea is provided for illustration.
Similar content being viewed by others
References
Abuzaid AH, Mohamed IB, Hussin AG (2012) Boxplot for circular variables. Comput Stat 27(3):381–392
Alegría A, Porcu E, Furrer R, Mateu J (2019) Covariance functions for multivariate Gaussian fields evolving temporally over planet earth. Stoch Environ Res Risk Assess 33(8–9):1593–1608
Anderson CM (1994) Graphical methods for circular and cylindrical data. In: Tech. Report TR-94-05, Department of Statistical and Actuarial Sciences, University of Western Ontario
Anselin L (1995) Local indicators of spatial association—LISA. Geogr Anal 27(2):93–115
Bowman AW, Crujeiras RM (2013) Inference for variograms. Comput Stat Data Anal 66:19–31
Buttarazzi D, Pandolfo G, Porzio GC (2018) A boxplot for circular data. Biometrics 74(4):1492–1501
Carnicero JA, Ausín MC, Wiper MP (2013) Non-parametric copulas for circular–linear and circular–circular data: an application to wind directions. Stoch Environ Res Risk Assess 27(8):1991–2002
Casson E, Coles S (1998) Extreme hurricane wind speeds: estimation, extrapolation and spatial smoothing. J Wind Eng Ind Aerodyn 74:131–140
Chacón JE, Duong T (2018) Multivariate kernel smoothing and its applications. CRC Press, Boca Raton
Cressie NA (1993) Statistics for spatial data. Wiley, New York
Di Marzio M, Panzera A, Taylor CC (2012) Non-parametric smoothing and prediction for nonlinear circular time series. J Time Ser Anal 33(4):620–630
Di Marzio M, Panzera A, Taylor CC (2013) Non-parametric regression for circular responses. Scand J Stat 40(2):238–255
Duong T (2015) Spherically symmetric multivariate beta family kernels. Stat Probab Lett 104:141–145
Emery X, Porcu E (2019) Simulating isotropic vector-valued Gaussian random fields on the sphere through finite harmonics approximations. Stoch Environ Res Risk Assess 33(8–9):1659–1667
Fernández-Casal R (2019) npsp: Nonparametric spatial (geo)statistics, R package version 0.7-5. http://cran.r-project.org/package=npsp. Accessed 14 Oct 2020
García-Portugués E, Barros AM, Crujeiras RM, González-Manteiga W, Pereira J (2014) A test for directional-linear independence, with applications to wildfire orientation and size. Stoch Environ Res Risk Assess 28(5):1261–1275
Hall P, Robinson AP (2009) Reducing variability of crossvalidation for smoothing parameter choice. Biometrika 96:175–186
Härdle W, Mammen E (1993) Comparing nonparametric versus parametric regression fits. Ann Stat 21:1926–1947
Härdle W, Müller M (2012) Multivariate and semiparametric kernel regression (chapter 12). Wiley, New York, pp 357–391
Hart JD, Vieu P (1990) Data-driven bandwidth choice for density estimation based on dependent data. Ann Stat 18(2):873–890
Jammalamadaka SR, SenGupta A (2001) Topics in circular statistics, vol 5. World Scientific, Singapore
Jona-Lasinio G, Gelfand A, Jona-Lasinio M (2012) Spatial analysis of wave direction data using wrapped Gaussian processes. Ann Appl Stat 6(4):1478–1498
Jona-Lasinio G, Mastrantonio G, Santoro M (2019) CircSpaceTime: spatial and spatio-temporal bayesian model for circular data, R package version 0.9.0. http://cran.r-project.org/package=CircSpaceTime. Accessed 14 Oct 2020
Kim S, SenGupta A (2017) Multivariate-multiple circular regression. J Stat Comput Simul 87(7):1277–1291
Lagarias JC, Reeds JA, Wright MH, Wright PE (1998) Convergence properties of the Nelder–Mead simplex method in low dimensions. SIAM J Optim 9(1):112–147
Lagona F, Picone M, Maruotti A, Cosoli S (2015) A hidden Markov approach to the analysis of space-time environmental data with linear and circular components. Stoch Environ Res Risk Assess 29(2):397–409
Leiva V, Sánchez L, Galea M, Saulo H (2020) Global and local diagnostic analytics for a geostatistical model based on a new approach to quantile regression. Stoch Environ Res Risk Assess 34(10):1457–1471
Liu XH (2001) Kernel smoothing for spatially correlated data. PhD thesis, Department of Statistics, Iowa State University
Martínez S, Giraldo R, Leiva V (2019) Birnbaum–Saunders functional regression models for spatial data. Stoch Environ Res Risk Assess 33(10):1765–1780
Mastrantonio G, Gelfand AE, Lasinio GJ (2016) The wrapped skew Gaussian process for analyzing spatio-temporal data. Stoch Environ Res Risk Assess 30(8):2231–2242
Mastrantonio G, Pollice A, Fedele F (2018) Distributions-oriented wind forecast verification by a hidden Markov model for multivariate circular–linear data. Stoch Environ Res Risk Assess 32(1):169–181
Meilán-Vila A, Francisco-Fernández M, Crujeiras R (2020a) Goodness-of-fit tests for parametric regression models with circular response. arXiv: 2008.13473
Meilán-Vila A, Francisco-Fernández M, Crujeiras R, Panzera A (2020b) Nonparametric multiple regression estimation for circular response. TEST. https://doi.org/10.1007/s11749-020-00736-w
Meilán-Vila A, Opsomer JD, Francisco-Fernández M, Crujeiras RM (2020c) A goodness-of-fit test for regression models with spatially correlated errors. TEST 29:728–749
Opsomer J, Wang Y, Yang Y (2001) Nonparametric regression with correlated errors. Stat Sci 16:134–153
Porcu E, Bevilacqua M, Genton MG (2016) Spatio-temporal covariance and cross-covariance functions of the great circle distance on a sphere. J Am Stat Assoc 111(514):888–898
R Development Core Team (2020) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna. http://www.R-project.org. Accessed 14 Oct 2020
Ruppert D, Wand MP (1994) Multivariate locally weighted least squares regression. Ann Stat 22:1346–1370
Saulo H, Leiva V, Ziegelmann FA, 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(6):1479–1491
Wang F, Gelfand AE (2014) Modeling space and space-time directional data using projected Gaussian processes. J Am Stat Assoc 109(508):1565–1580
Acknowledgements
The authors acknowledge the support from the Xunta de Galicia Grant ED481A-2017/361 and the European Union (European Social Fund—ESF). This research has been partially supported by MINECO Grants MTM2016-76969-P and MTM2017-82724-R, and by the Xunta de Galicia (Grupos de Referencia Competitiva ED431C-2016-015, ED431C-2017-38 and ED431C-2020-14, and Centro de Investigación del SUG ED431G 2019/01), all of them through the ERDF. The authors thank Prof. Agnese Panzera, from the University of Florence, for her help in the theoretical developments of the paper and her general comments about this work. The authors also thank an Associate Editor and two anonymous referees for numerous useful comments that significantly improved this article.
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: Proof of Theorem 1
Appendix: Proof of Theorem 1
Proof
Before deriving the asymptotic variance of the estimator \({\hat{m}}_{{\varvec{H}}}({\varvec{x}},p)\), for \(p=0,1\), stated in Theorem 1, some preliminary approximations are needed.
Firstly, defining \(f_1({\varvec{x}})=\sin [m({\varvec{x}})]\) and \(f_2({\varvec{x}})=\cos [m({\varvec{x}})]\), using sine and cosine addition formulas, the following relation between the covariance function \(C_{n,3}\), defined from models (6) and (7), and the correlations \({\rho _{k,n}}\), \(k=1,2,3\), directly derived from model (1) and given in (2), (3) and (4), can be obtained:
Moreover, denoting
and, after some calculations, it can be obtained that
where \({\varvec{1}}_d\) and \({\varvec{1}}_{d\times d}\) denote the \(d\times 1\) vector and the \(d\times d\) matrix with every entry equal to 1, and
To derive the variance of \({\hat{m}}_{{\varvec{H}}}({\varvec{x}};p)\), for \(p=0,1\), denoting by \({\varvec{\mathcal {X}}}=({\varvec{X}}_1,\dots ,{\varvec{X}}_n)\), using Taylor expansions and following similar arguments to those used in Di Marzio et al. (2013) and Meilán-Vila et al. (2020b), it can be obtained that
The conditional variance of \({\hat{m}}_{j, {\varvec{H}}}({\varvec{x}};p)\), for \(j=1,2\), and \(p=0,1,\) for spatially correlated data, can be derived using similar arguments to those given in Liu (2001), which yield
where
Moreover, using (19) and (22), it is easy to obtain that the conditional covariance between \({\hat{m}}_{1, {\varvec{H}}}({\varvec{x}};0)\) and \({\hat{m}}_{2, {\varvec{H}}}({\varvec{x}};0)\) is
On the other hand, the conditional covariance between \({\hat{m}}_{1, {\varvec{H}}}({\varvec{x}};1)\) and \({\hat{m}}_{2, {\varvec{H}}}({\varvec{x}};1)\) is
where \({\varvec{\varSigma }}\) is the covariance matrix of \(\sin (\varTheta )\) and \(\cos (\varTheta )\), whose (i, j)-entry is \({\varvec{\varSigma }}(i,j)={\mathbb {C}}{\text {ov}}[\sin (\varTheta _i),\cos (\varTheta _j)],\) \(i,j=1,\dots ,n.\) Using (19), (20), (21), (22), (23) and (24), it follows that
and that
Consequently, by straightforward calculations, one gets that
Using (27), (28), (33) and (34), one gets that, for \(p=0,1\),
Notice that it holds that
Taking into account that \(f^2_1({\varvec{x}})+f_2^2({\varvec{x}})=1\), it can be easily deduced that \(\ell ({\varvec{x}})=[m^2_1({\varvec{x}})+m_2^2({\varvec{x}})]^{1/2}\). Therefore, using (25), (26), (29), (30), (31), (32) and (35), it follows that
Consequently, it can be directly obtained that
□
Rights and permissions
About this article
Cite this article
Meilán-Vila, A., Crujeiras, R.M. & Francisco-Fernández, M. Nonparametric estimation of circular trend surfaces with application to wave directions. Stoch Environ Res Risk Assess 35, 923–939 (2021). https://doi.org/10.1007/s00477-020-01919-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-020-01919-5