Soap Film Smoothing

Journal of the Royal Statistical Society. Series B: Statistical Methodology - Tập 70 Số 5 - Trang 931-955 - 2008
Simon N. Wood1, Mark V. Bravington2, Sharon L. Hedley3
1University of Bath, UK
2Commonwealth Scientific and Industrial Research Organisation, Hobart, Australia
3University of St. Andrews, UK

Tóm tắt

SummaryConventional smoothing methods sometimes perform badly when used to smooth data over complex domains, by smoothing inappropriately across boundary features, such as peninsulas. Solutions to this smoothing problem tend to be computationally complex, and not to provide model smooth functions which are appropriate for incorporating as components of other models, such as generalized additive models or mixed additive models. We propose a class of smoothers that are appropriate for smoothing over difficult regions of R2 which can be represented in terms of a low rank basis and one or two quadratic penalties. The key features of these smoothers are that they do not ‘smooth across’ boundary features, that their representation in terms of a basis and penalties allows straightforward incorporation as components of generalized additive models, mixed models and other non-standard models, that smoothness selection for these model components is straightforward to accomplish in a computationally efficient manner via generalized cross-validation, Akaike's information criterion or restricted maximum likelihood, for example, and that their low rank means that their use is computationally efficient.

Từ khóa


Tài liệu tham khảo

Bowman, 1997, Applied Smoothing Techniques for Data Analysis, 10.1093/oso/9780198523963.001.0001

Dixon, 2003, Multi-dimensional modelling of physiologically and temporally structured populations

Duchon, 1977, Construction Theory of Functions of Several Variables, 85, 10.1007/BFb0086566

Eilers, 2006, P-spline smoothing on difficult domains

Eilers, 1996, Flexible smoothing with B-splines and penalties, Statist. Sci., 11, 89, 10.1214/ss/1038425655

Evans, 1998, Partial Differential Equations

Fahrmeir, 2004, Penalized structured additive regression for space-time data: a Bayesian perspective, Statist. Sin., 14, 731

Green, 1994, Nonparametric Regression and Generalized Linear Models, 10.1007/978-1-4899-4473-3

Gu, 2002, Smoothing Spline ANOVA Models, 10.1007/978-1-4757-3683-0

Hastie, 1990, Generalized Additive Models

Horwood, 1993, The Bristol Channel Sole (Solea solea (l.)): a fisheries case study, Adv. Mar. Biol., 29, 215, 10.1016/S0065-2881(08)60132-7

Horwood, 1990, Determinacy of fecundity in Sole (Solea solea) from the Bristol Channel, J. Mar. Biol. Ass. UK, 70, 803, 10.1017/S0025315400059075

Kim, 2004, Smoothing spline Gaussian regression: more scalable computation via efficient approximation, J. R. Statist. Soc. B, 66, 337, 10.1046/j.1369-7412.2003.05316.x

Press, 1992, Numerical Recipes in C, 2nd edn

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

Ramsay, 1999, A bivariate finite element smoothing spline applied to image restoration

Ramsay, 2002, Spline smoothing over difficult regions, J. R. Statist. Soc. B, 64, 307, 10.1111/1467-9868.00339

Ruppert, 2003, Semiparametric Regression, 10.1017/CBO9780511755453

Silverman, 1985, Some aspects of the spline smoothing approach to non-parametric regression curve fitting (with discussion), J. R. Statist. Soc. B, 47, 1

Stone, 1988, Bivariate splines

Strauss, 1992, Partial Differential Equations: an Introduction

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

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

Wang, 2007, Low-rank smoothing splines on complicated domains, Biometrics, 63, 209, 10.1111/j.1541-0420.2006.00674.x

Wood, 2003, Thin plate regression splines, J. R. Statist. Soc. B, 65, 95, 10.1111/1467-9868.00374

Wood, 2004, Stable and efficient multiple smoothing parameter estimation for generalized additive models, J. Am. Statist. Ass., 99, 673, 10.1198/016214504000000980

Wood, 2006, Generalized Additive Models: an Introduction with R, 10.1201/9781420010404

Wood, 2006, On confidence intervals for generalized additive models based on penalized regression splines, Aust. New Zeal. J. Statist., 48, 445, 10.1111/j.1467-842X.2006.00450.x

Wood, 2008, J. R. Statist. Soc. B, 70, 495, 10.1111/j.1467-9868.2007.00646.x

Thông tin
Thông tin xuất bản

Journal of the Royal Statistical Society. Series B: Statistical Methodology

Tập 70 Số 5

931-955

Thông tin tác giả