Bernoulli

  • Bernoulli
  • Volume 19, Number 5B (2013), 2250-2276.

Uniform convergence of convolution estimators for the response density in nonparametric regression

Anton Schick and Wolfgang Wefelmeyer

Full-text: Open access

Abstract

We consider a nonparametric regression model $Y=r(X)+\varepsilon$ with a random covariate $X$ that is independent of the error $\varepsilon$. Then the density of the response $Y$ is a convolution of the densities of $\varepsilon$ and $r(X)$. It can therefore be estimated by a convolution of kernel estimators for these two densities, or more generally by a local von Mises statistic. If the regression function has a nowhere vanishing derivative, then the convolution estimator converges at a parametric rate. We show that the convergence holds uniformly, and that the corresponding process obeys a functional central limit theorem in the space $C_{0}(\mathbb{R})$ of continuous functions vanishing at infinity, endowed with the sup-norm. The estimator is not efficient. We construct an additive correction that makes it efficient.

Article information

Source
Bernoulli, Volume 19, Number 5B (2013), 2250-2276.

Dates
First available in Project Euclid: 3 December 2013

Permanent link to this document
https://projecteuclid.org/euclid.bj/1386078602

Digital Object Identifier
doi:10.3150/12-BEJ451

Mathematical Reviews number (MathSciNet)
MR3160553

Zentralblatt MATH identifier
1281.62103

Keywords
density estimator efficient estimator efficient influence function functional central limit theorem local polynomial smoother local U-statistic local von Mises statistic monotone regression function

Citation

Schick, Anton; Wefelmeyer, Wolfgang. Uniform convergence of convolution estimators for the response density in nonparametric regression. Bernoulli 19 (2013), no. 5B, 2250--2276. doi:10.3150/12-BEJ451. https://projecteuclid.org/euclid.bj/1386078602


Export citation

References

  • [1] Bickel, P.J., Klaassen, C.A.J., Ritov, Y. and Wellner, J.A. (1998). Efficient and Adaptive Estimation for Semiparametric Models. New York: Springer. Reprint of the 1993 original.
  • [2] Bickel, P.J. and Ritov, Y. (1988). Estimating integrated squared density derivatives: Sharp best order of convergence estimates. Sankhyā Ser. A 50 381–393.
  • [3] Chaudhuri, P., Doksum, K. and Samarov, A. (1997). On average derivative quantile regression. Ann. Statist. 25 715–744.
  • [4] Efromovich, S. and Samarov, A. (2000). Adaptive estimation of the integral of squared regression derivatives. Scand. J. Statist. 27 335–351.
  • [5] Escanciano, J.C. and Jacho-Chávez, D.T. (2012). $\sqrt{n}$-uniformly consistent density estimation in nonparametric regression models. J. Econometrics 167 305–316.
  • [6] Frees, E.W. (1994). Estimating densities of functions of observations. J. Amer. Statist. Assoc. 89 517–525.
  • [7] Giné, E. and Mason, D.M. (2007). On local $U$-statistic processes and the estimation of densities of functions of several sample variables. Ann. Statist. 35 1105–1145.
  • [8] Laurent, B. (1996). Efficient estimation of integral functionals of a density. Ann. Statist. 24 659–681.
  • [9] Müller, U.U. (2012). Estimating the density of a possibly missing response variable in nonlinear regression. J. Statist. Plann. Inference 142 1198–1214.
  • [10] Müller, U.U., Schick, A. and Wefelmeyer, W. (2009). Estimating the error distribution function in nonparametric regression with multivariate covariates. Statist. Probab. Lett. 79 957–964.
  • [11] Müller, U.U., Schick, A. and Wefelmeyer, W. (2013). Non-standard behavior of density estimators for functions of independent observations. Comm. Statist. Theory Methods 42 2991–3000.
  • [12] Nickl, R. (2007). Donsker-type theorems for nonparametric maximum likelihood estimators. Probab. Theory Related Fields 138 411–449. Erratum: Probab. Theory Related Fields 141 (2008) 331–332.
  • [13] Nickl, R. (2009). On convergence and convolutions of random signed measures. J. Theoret. Probab. 22 38–56.
  • [14] Saavedra, Á. and Cao, R. (1999). Rate of convergence of a convolution-type estimator of the marginal density of an MA(1) process. Stochastic Process. Appl. 80 129–155.
  • [15] Saavedra, A. and Cao, R. (2000). On the estimation of the marginal density of a moving average process. Canad. J. Statist. 28 799–815.
  • [16] Schick, A. (1993). On efficient estimation in regression models. Ann. Statist. 21 1486–1521. Correction and Addendum: Ann. Statist. 23 (1995) 1862–1863.
  • [17] Schick, A. and Wefelmeyer, W. (2004). Functional convergence and optimality of plug-in estimators for stationary densities of moving average processes. Bernoulli 10 889–917.
  • [18] Schick, A. and Wefelmeyer, W. (2004). Root $n$ consistent and optimal density estimators for moving average processes. Scand. J. Statist. 31 63–78.
  • [19] Schick, A. and Wefelmeyer, W. (2004). Root $n$ consistent density estimators for sums of independent random variables. J. Nonparametr. Stat. 16 925–935.
  • [20] Schick, A. and Wefelmeyer, W. (2007). Root-$n$ consistent density estimators of convolutions in weighted $L_{1}$-norms. J. Statist. Plann. Inference 137 1765–1774.
  • [21] Schick, A. and Wefelmeyer, W. (2007). Uniformly root-$n$ consistent density estimators for weakly dependent invertible linear processes. Ann. Statist. 35 815–843.
  • [22] Schick, A. and Wefelmeyer, W. (2008). Root-$n$ consistency in weighted $L_{1}$-spaces for density estimators of invertible linear processes. Stat. Inference Stoch. Process. 11 281–310.
  • [23] Schick, A. and Wefelmeyer, W. (2009). Convergence rates of density estimators for sums of powers of observations. Metrika 69 249–264.
  • [24] Schick, A. and Wefelmeyer, W. (2009). Non-standard behavior of density estimators for sums of squared observations. Statist. Decisions 27 55–73.
  • [25] Støve, B. and Tjøstheim, D. (2012). A convolution estimator for the density of nonlinear regression observations. Scand. J. Statist. 39 282–304.