Abstract
We consider a problem of estimating local smoothness of a spatially inhomogeneous function from noisy data under the framework of smoothing splines. Most existing studies related to this problem deal with estimation induced by a single smoothing parameter or partially local smoothing parameters, which may not be efficient to characterize various degrees of smoothness of the underlying function when it is spatially varying. In this paper, we propose a new nonparametric method to estimate local smoothness of the function based on a moving local risk minimization coupled with spatially adaptive smoothing splines. The proposed method provides full information of the local smoothness at every location on the entire data domain, so that it is able to understand the degrees of spatial inhomogeneity of the function. A successful estimate of the local smoothness is useful for identifying abrupt changes of smoothness of the data, performing functional clustering and improving the uniformity of coverage of the confidence intervals of smoothing splines. We further consider a nontrivial extension of the local smoothness of inhomogeneous two-dimensional functions or spatial fields. Empirical performance of the proposed method is evaluated through numerical examples, which demonstrates promising results of the proposed method.
Similar content being viewed by others
References
Antoniadis A, Brossat X, Cugliari J, Poggi JM (2013) Clustering functional data using wavelets. Int J Wavelets Multiresolut Inf Process 11(01):1350003
Chaudhuri P, Marron JS (1999) SiZer for exploration of structures in curves. J Am Stat Assoc 94:807–823
Cuevas A (2014) A partial overview of the theory of statistics with functional data. J Stat Plan Inference 147:1–23
Cummins DJ, Filloon TG, Nychka D (2001) Confidence intervals for nonparametric curve estimates: toward more uniform pointwise coverage. J Am Stat Assoc 96:233–246
Donoho DL, Johnstone IM (1994) Ideal spatial adaptation by wavelet shrinkage. Biometrika 81:425–455
Donoho DL, Johnstone IM, Kerkyacharian G, Picard D (1995) Wavelet shrinkage: asymptopia? J R Stat Soc Series B 57:301–369
Erästö P, Holmström L (2005) Bayesian multiscale smoothing for making inferences about features in scatter plots. J Comput Graph Stat 14:569–589
Fan J, Gijbels I (1996) Local polynomial modelling and its applications. Chapman & Hall, London
Fryzlewicz P, Oh H-S (2011) Thick-pen transform for time series. J R Stat Soc Series B 73:499–529
Giacofci M, Lambert-Lacroix S, Marot G, Picard F (2013) Wavelet-based clustering for mixed-effects functional models in high dimension. Biometrics 69:31–40
Goia A, Vieu P (2016) An introduction to recent advances in high/infinite dimensional statistics. J Multivar Stat 146:1–6
Green PJ, Silverman BW (1994) Nonparametric regression and generalized linear models. Chapman & Hall, London
Hannig J, Lee TCM (2006) Robust SiZer for exploration of regression structures and outlier detection. J Comput Graph Stat 15:101–117
Hannig J, Lee T, Park C (2013) Metrics for SiZer map comparison. Stat 2:49–60
Holmström L (2010a) BSiZer. Wiley Interdiscip Rev Comput Stat 2:526–534
Holmströma L (2010b) Scale space methods. Wiley Interdiscip Rev Comput Stat 2:150–159
Holmströma L, Pasanena L (2016) Statistical scale space methods. Int Stat Rev. doi:10.1111/insr.12155
James GM, Sugar CA (2003) Clustering for sparsely sampled functional data. J Am Stat Assoc 98:397–408
Jang D, Oh H-S (2011) Enhancement of spatially adaptive smoothing splines via parameterization of smoothing parameters. Comput Stat Data Anal 55:1029–1040
Jaques J, Preda C (2013) Functional data clustering: a survey. Adv Data Anal Classif 8:231–255
Lee TCM (2004) Improved smoothing spline regression by combining estimates of different smoothness. Stat Probab Lett 67:133–140
Lindeberg T (1994) Scale-space theory in computer vision. Kluwer, Boston
Morris JS, Carroll RJ (2006) Wavelet-based functional mixed models. J R Stat Soc Series B 68:179–199
Pasanena L, Launonena I, Holmströma L (2013) A scale space multiresolution method for extraction of time series features. Stat 2:273–291
Park C, Hannig J, Kang KH (2009) Improved SiZer for time series. Stat Sin 19:1511–1530
Park C, Lee TC, Hannig J (2010) Multiscale exploratory analysis of regression quantiles using quantile SiZer. J Comput Graph Stat 19:497–513
Pintore A, Speckman P, Holmes CC (2006) Spatially adaptive smoothing splines. Biometrika 93:113–125
Ray S, Mallick B (2006) Functional clustering by Bayesian wavelet methods. J R Stat Soc Series B 68:305–332
Sain SR (2002) Multivariate locally adaptive density estimation. Comput Stat Data Anal 39:165–186
Sain SR, Scott DW (1996) On locally adaptive density estimation. J Am Stat Assoc 91:1525–1534
Serban N, Wasserman L (2005) CATS: cluster analysis by transformation and smoothing. J Am Stat Assoc 100:990–999
Smith M, Kohn R (1996) Nonparametric regression using Bayesian variable selection. J Econ 75:317–344
Wahba G (1983) Bayesian ‘confidence intervals’ for the cross-validated smoothing spline. J R Stat Soc Series B 45:133–150
Wahba G (1990) Spline models for observational data. In: CBMS-NSF, regional conference series in applied mathematics. SIAM, Philadelphia
Wahba G (1995) Discussion of a paper by Donoho et al. J R Stat Soc Series B 57:360–361
Wakefield J, Zhou C, Self S (2003) Modelling gene expression over time: curve clustering with informative prior distributions. In: Bernardo J, Bayarri M, Berger J, Dawid A, Heckerman D, Smith A, West M (eds) Bayesian statistics, vol 7. Oxford University Press, Oxford, pp 721–732
Acknowledgments
This work was supported in part by the National Research Foundation of Korea (NRF) Grant funded by the Korea government (MSIP) (Nos. NRF-2015R1D1A1A01056854 and 20110030811).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jang, D., Oh, HS. & Naveau, P. Identifying local smoothness for spatially inhomogeneous functions. Comput Stat 32, 1115–1138 (2017). https://doi.org/10.1007/s00180-016-0694-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-016-0694-y