Smooth backfitting in practice

Compared with the classical backfitting of Buja, Hastie and Tibshirani, the smooth backfitting estimator (SBE) of Mammen, Linton and Nielsen not only provides complete asymptotic theory under weaker conditions but is also more efficient, robust and easier to calculate. However, the original paper describing the SBE method is complex and the practical as well as the theoretical advantages of the method have still neither been recognized nor accepted by the statistical community. We focus on a clear presentation of the idea, the main theoretical results and practical aspects like implementation and simplification of the algorithm. We introduce a feasible cross-validation procedure and apply it to the problem of data-driven bandwidth choice for the SBE. By simulations it is shown that the SBE and our cross-validation work very well indeed. In particular, the SBE is less affected by sparseness of data in high dimensional regression problems or strongly correlated designs. The SBE has reasonable performance even in 100-dimensional additive regression problems. Copyright 2005 Royal Statistical Society.

[1]  Stefan Sperlich.  Additive Modelling and Testing Model Specification , 1998 .

[2]  Jean D. Opsomer,et al.  Asymptotic Properties of Backfitting Estimators , 2000 .

[3]  Dag Tjøstheim,et al.  NONPARAMETRIC ESTIMATION AND TESTING OF INTERACTION IN ADDITIVE MODELS , 2002, Econometric Theory.

[4]  C. J. Stone,et al.  Additive Regression and Other Nonparametric Models , 1985 .

[5]  W. Härdle,et al.  How Far are Automatically Chosen Regression Smoothing Parameters from their Optimum , 1988 .

[6]  Oliver Linton,et al.  Miscellanea Efficient estimation of additive nonparametric regression models , 1997 .

[7]  Carsten von Lieres und Wilkau,et al.  A comparison of different nonparametric methods for inference on additive models , 2005 .

[8]  Enno Mammen,et al.  The Existence and Asymptotic Properties of a Backfitting Projection Algorithm Under Weak Conditions , 1999 .

[9]  Enno Mammen,et al.  Bandwidth selection for smooth backfitting in additive models , 2005, math/0507425.

[10]  Oliver Linton,et al.  Integration and backfitting methods in additive models-finite sample properties and comparison , 1999 .

[11]  Nicolas W. Hengartner,et al.  Rate optimal estimation with the integration method in the presence of many covariates , 2005 .

[12]  J. Muellbauer,et al.  Economics and consumer behavior , 1980 .

[13]  R. Tibshirani,et al.  Linear Smoothers and Additive Models , 1989 .

[14]  W. Newey,et al.  Kernel Estimation of Partial Means and a General Variance Estimator , 1994, Econometric Theory.

[15]  R. Tibshirani,et al.  Generalized additive models for medical research , 1986, Statistical methods in medical research.

[16]  Jens Perch Nielsen,et al.  An optimization interpretation of integration and back‐fitting estimators for separable nonparametric models , 1998 .

[17]  O. Linton,et al.  A kernel method of estimating structured nonparametric regression based on marginal integration , 1995 .

[18]  E. Mammen,et al.  Generalised structured models , 2003 .

[19]  David Ruppert,et al.  Fitting a Bivariate Additive Model by Local Polynomial Regression , 1997 .

[20]  E. Mammen,et al.  A General Projection Framework for Constrained Smoothing , 2001 .

[21]  Dag Tjøstheim,et al.  Nonparametric Identification of Nonlinear Time Series: Projections , 1994 .

[22]  Qi Li,et al.  Nonparametric Econometrics: Theory and Practice , 2006 .