• Bernoulli
  • Volume 12, Number 2 (2006), 271-298.

Optimal estimation in additive regression models

Joel Horowitz,, Jussi Klemelä, and Enno Mammen

Full-text: Open access


This paper is concerned with optimal estimation of the additive components of a nonparametric, additive regression model. Several different smoothing methods are considered, including kernels, local polynomials, smoothing splines and orthogonal series. It is shown that, asymptotically up to first order, each additive component can be estimated as well as it could be if the other components were known. This result is used to show that in additive models the asymptotically optimal minimax rates and constants are the same as they are in nonparametric regression models with one component.

Article information

Bernoulli, Volume 12, Number 2 (2006), 271-298.

First available in Project Euclid: 25 April 2006

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

exact constants in nonparametric smoothing kernel estimators multivariate curve estimation nonparametric regression orthogonal series estimator smoothing splines


Horowitz,, Joel; Klemelä, Jussi; Mammen, Enno. Optimal estimation in additive regression models. Bernoulli 12 (2006), no. 2, 271--298. doi:10.3150/bj/1145993975.

Export citation


  • [1] Belitser, E.N. and Levit, B.Y. (1995) On minimax filtering over ellipsoids. Math. Methods Statist., 4, 259-273.
  • [2] Efromovich, S. (1996) On nonparametric regression for iid observations in a general setting. Ann. Statist., 24, 1126-1144.
  • [3] Efromovich, S. and Pinsker, M.S. (1984) Learning algorithm for nonparametric filtering. Avtomat. i Telemekh., 11, 58-65.
  • [4] Golubev, G.K. (1987) Adaptive asymptotically minimax estimators of smooth signals. Problems Inform. Transmission, 23, 57-67.
  • [5] Golubev, G.K. (1992) Asymptotic minimax estimation of regression in the additive model. Problemy Peredachi Informatsii, 28, 3-15 (in Russian). English translation: Problems Inform. Transmission, 28, 101-112 (1992).
  • [6] Golubev, G.K. and Nussbaum, M. (1990) A risk bound in Sobolev class regression. Ann. Statist., 18, 758-778.
  • [7] Hastie, T. and Tibshirani, R. (1991) Generalized Additive Models. London: Chapman & Hall.
  • [8] Horowitz, J. and Mammen, E. (2004) Nonparametric estimation of an additive model with a link function. Ann. Statist., 32, 2412-2443.
  • [9] Linton, O. (2000) Efficient estimation of generalized additive nonparametric regression models. Econometric Theory, 16, 502-523.
  • [10] Mammen, E., Linton, O. and Nielsen, J. (1999) The existence and asymptotic properties of a backfitting projection algorithm under weak conditions. Ann. Statist., 27, 1443-1490.
  • [11] Nussbaum, M. (1985) Spline smoothing in regression models and asymptotic efficiency in L2. Ann. Statist., 13, 984-997.
  • [12] Opsomer, J.D. (2000) Asymptotic properties of backfitting estimators. J. Multivariate Anal., 73, 166- 179.
  • [13] Opsomer, J.D. and Ruppert, D. (1997) Fitting a bivariate additive model by local polynomial regression. Ann. Statist., 25, 185-211.
  • [14] Pinsker, M.S. (1980) Optimal filtering of square integrable signals in Gaussian white noise. Problemy Peredachi Informatsii, 16, 52-68 (in Russian). English translation: Problems Inform. Transmission, 16, 120-133 (1980).
  • [15] Shorack, G.R. and Wellner, J.A. (1986) Empirical Processes with Applications to Statistics. New York: Wiley.
  • [16] Stone, C.J. (1985) Additive regression and other nonparametric models. Ann. Statist., 13, 689-705.
  • [17] van de Geer, S. (2000) Empirical Processes in M-Estimation. Cambridge: Cambridge University Press.
  • [18] Zhang, S. and Wong, M.-Y. (2003) Wavelet threshold estimation for additive regression models. Ann. Statist., 31, 152-173.