Spline Smoothing over Difficult Regions

Tim Ramsay1
1McLaughlin Centre for Population Health Risk Assessment, Ottawa, Canada

Tóm tắt

SummaryIt is occasionally necessary to smooth data over domains in ℝ2 with complex irregular boundaries or interior holes. Traditional methods of smoothing which rely on the Euclidean metric or which measure smoothness over the entire real plane may then be inappropriate. This paper introduces a bivariate spline smoothing function defined as the minimizer of a penalized sum-of-squares functional. The roughness penalty is based on a partial differential operator and is integrated only over the problem domain by using finite element analysis. The method is motivated by and applied to two sample smoothing problems and is compared with the thin plate spline.

Từ khóa


Tài liệu tham khảo

Braess, 1997, Finite Elements: Theory, Fast Solvers, and Applications in Solid Mechanics, 10.1007/978-3-662-07233-2

Brenner, 1994, The Mathematical Theory of Finite Elements, 10.1007/978-1-4757-4338-8

Carey, 1983, Finite Elements: a Second Course

Cowling, 1996, Applications of spatial smoothing to survey data, Surv. Methodol., 22, 175

Dierkcx, 1993, Curve and Surface Fitting with Splines

Duchon, 1976, Interpolation des fonctions de deux variables suivant le principe de la flexion des placques minces, Rev. Fr. Autom. Inform. Rech. Oper. Anal. Numer., 10, 5

Dyn, 1982, Construction of surface spline interpolants of scattered data over finite domains, Rev. Fr. Autom. Inform. Rech. Oper. Anal. Numer., 16, 201

Folland, 1995, Introduction to Partial Differential Equations

Hanselman, 1998, Mastering MATLAB 5: a Comprehensive Tutorial and Reference

Heckman, 2000, Penalized regression with model-based penalties, Can. J. Statist., 28, 241, 10.2307/3315976

Hinkley, 1988, Bootstrap methods, J. R. Statist. Soc., 50, 321

Horgan, 1999, Using wavelets for data smoothing: a simulation study, J. Appl. Statist., 26, 923, 10.1080/02664769921936

Meiring, 1997, Computing Science and Statistics; Mining and Modeling Massive Data Sets in Science, Engineering, and Business with a Subtheme in Environmental Science: Proc. 29th Symp. Interface, 409

Connell, 1997, Spatial regression models, response surfaces, and process optimization, J. Comput. Graph. Statist., 6, 224

Ramsay, 2000, Differential equation models for statistical functions, Can. J. Statist., 28, 224, 10.2307/3315975

Sibson, 1991, Computation of thinplate splines, SIAM J. Statist. Scient. Comput., 12, 1304, 10.1137/0912070

Stone, 1988, Bivariate splines

Wahba, 1990, Spline Models for Observational Data, 10.1137/1.9781611970128

Wand, 1995, Kernel Smoothing, 10.1007/978-1-4899-4493-1