Derivative Estimation and Testing in Generalized Additive Models

Estimation and testing procedures for generalized additive (interaction) models are developed. We present extensions of several existing procedures for additive models when the link is the identity. This set of methods includes estimation of all component functions and their derivatives, testing functional forms and in particular variable selection. Theorems and simulation results are presented for the fundamentally new procedures. These comprise of, in particular, the introduction of local polynomial smoothing for this kind of models and the testing, including variable selection. Our method is straightforward to implement and the simulation studies show good performance in even small data sets.

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

[2]  W. Härdle,et al.  Estimation of additive regression models with known links , 1996 .

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

[4]  James Stephen Marron,et al.  BOOTSTRAP SIMULTANEOUS ERROR BARS FOR NONPARAMETRIC REGRESSION , 1991 .

[5]  Changbao Wu,et al.  Jackknife, Bootstrap and Other Resampling Methods in Regression Analysis , 1986 .

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

[7]  James Stephen Marron,et al.  Canonical kernels for density estimation , 1988 .

[8]  Lijian Yang,et al.  Multivariate bandwidth selection for local linear regression , 1999 .

[9]  C. J. Stone,et al.  The Dimensionality Reduction Principle for Generalized Additive Models , 1986 .

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

[11]  Regina Y. Liu Bootstrap Procedures under some Non-I.I.D. Models , 1988 .

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

[13]  E. Mammen,et al.  Comparing Nonparametric Versus Parametric Regression Fits , 1993 .

[14]  D. Andrews,et al.  Additive Interactive Regression Models: Circumvention of the Curse of Dimensionality , 1990, Econometric Theory.

[15]  Oliver Linton,et al.  Testing Additivity in Generalized Nonparametric Regression Models , 1995 .

[16]  R. Tibshirani,et al.  Generalized Additive Models , 1991 .

[17]  Dag Tjøstheim,et al.  Linearity Testing using Local Polynomial Approximation , 1998 .

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

[19]  J. Marron,et al.  SiZer for Exploration of Structures in Curves , 1999 .

[20]  Stefan Sperlich,et al.  Estimation of Derivatives for Additive Separable Models , 1999 .

[21]  M. Wand,et al.  Multivariate Locally Weighted Least Squares Regression , 1994 .

[22]  C. J. Stone,et al.  The Use of Polynomial Splines and Their Tensor Products in Multivariate Function Estimation , 1994 .

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

[24]  E. Mammen,et al.  Semiparametric additive indices for binary response and generalized additive models , 1998 .

[25]  Wolfgang Härdle,et al.  BOOTSTRAP INFERENCE IN SEMIPARAMETRIC GENERALIZED ADDITIVE MODELS , 2004, Econometric Theory.

[26]  P. Hall Central limit theorem for integrated square error of multivariate nonparametric density estimators , 1984 .

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

[28]  Wolfgang Härdle,et al.  Direct estimation of low-dimensional components in additive models , 1998 .