• Bernoulli
  • Volume 14, Number 2 (2008), 562-579.

Density estimation with heteroscedastic error

Aurore Delaigle and Alexander Meister

Full-text: Open access


It is common, in deconvolution problems, to assume that the measurement errors are identically distributed. In many real-life applications, however, this condition is not satisfied and the deconvolution estimators developed for homoscedastic errors become inconsistent. In this paper, we introduce a kernel estimator of a density in the case of heteroscedastic contamination. We establish consistency of the estimator and show that it achieves optimal rates of convergence under quite general conditions. We study the limits of application of the procedure in some extreme situations, where we show that, in some cases, our estimator is consistent, even when the scaling parameter of the error is unbounded. We suggest a modified estimator for the problem where the distribution of the errors is unknown, but replicated observations are available. Finally, an adaptive procedure for selecting the smoothing parameter is proposed and its finite-sample properties are investigated on simulated examples.

Article information

Bernoulli, Volume 14, Number 2 (2008), 562-579.

First available in Project Euclid: 22 April 2008

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

bandwidth density deconvolution errors-in-variables heteroscedastic contamination inverse problems plug-in


Delaigle, Aurore; Meister, Alexander. Density estimation with heteroscedastic error. Bernoulli 14 (2008), no. 2, 562--579. doi:10.3150/08-BEJ121.

Export citation


  • Bennett, C.A. and Franklin, N.L. (1954)., Statistical Analysis in Chemistry and the Chemical Industry. New York: Wiley.
  • Butucea, C. and Matias, C. (2005). Minimax estimation of the noise level and of the deconvolution density in a semiparametric convolution model., Bernoulli 11 309–340.
  • Carroll, R.J., Eltinge, J.L. and Ruppert D. (1993). Robust linear regression in replicated measurement error models., Statist. Probab. Lett. 16 169–175.
  • Carroll, R.J. and Hall, P. (1988). Optimal rates of convergence for deconvolving a density., J. Amer. Statist. Assoc. 83 1184–1186.
  • Carroll, R.J. and Hall, P. (2004). Low-order approximations in deconvolution and regression with errors in variables., J. Roy. Statist. Soc. Ser. B 66 31–46.
  • Carroll, R.J., Ruppert, D., Stefanski, L.A. and Crainiceanu, C.M. (2006)., Measurement Error in Nonlinear Models, 2nd ed. Boca Raton, FL: Chapman and Hall CRC Press.
  • Delaigle, A. (2008). An alternative view of the deconvolution problem., Statist. Sinica 36 665–685.
  • Delaigle, A. and Gijbels, I. (2004). Comparison of data-driven bandwidth selection procedures in deconvolution kernel density estimation., Comput. Statist. Data Anal. 45 249–267.
  • Delaigle, A., Hall, P. and Meister, A. (2008). On deconvolution with repeated measurements., Ann. Statist. 36 665–685.
  • Delaigle, A., Hall, P. and Müller, H.G. (2007). Accelerated convergence for nonparametric regression with coarsened predictors., Ann. Statist. 35 2639–2653.
  • Delaigle, A. and Meister, A. (2007). Density estimation with heteroscedastic error. Long version available from the, authors.
  • Devroye, L. (1987)., A Course in Density Estimation. Boston: Birkhäuser.
  • Diggle, P. and Hall, P. (1993). A Fourier approach to nonparametric deconvolution of a density estimate., J. Roy. Statist. Soc. Ser. B 55 523–531.
  • van Es, A.J. and Uh, H.-W. (2005). Asymptotic normality of kernel type deconvolution estimators., Scand. J. Statist. 32 467–483.
  • Fan, J. (1991a). Global behaviour of deconvolution kernel estimates., Statist. Sinica 1 541–551.
  • Fan, J. (1991b). On the optimal rates of convergence for nonparametric deconvolution problems., Ann. Statist. 19 1257–1272.
  • Fan, J. (1993). Adaptively local one-dimensional subproblems with application to a deconvolution problem., Ann. Statist. 21 600–610.
  • Fuller, W.A. (1987)., Measurement Error Models. New York: Wiley.
  • Hall, P. and Meister, A. (2007). A ridge-parameter approach to deconvolution., Ann. Statist. 35 1535–1558.
  • Hall, P. and Qiu, P. (2005). Discrete-transform approach to deconvolution problems., Biometrika 92 135–148.
  • Hesse, C.H. (1996). How many “good” observations do you need for a “fast” density deconvolution from supersmooth errors., Sankhyā Ser. A 58 491–506.
  • Horowitz, J.L. and Markatou, M. (1996). Semiparametric estimation of regression models for panel data., Rev. Econom. Stud. 63 145–168.
  • Lukacs, E. (1970)., Characteristic Functions, 2nd ed. New York: Hafner Publishing Co.
  • Masry, E. (1993). Asymptotic normality for deconvolution estimators of multivariate densities of stationary processes., J. Multivariate Anal. 44 47–68.
  • Meister, A. (2006). Density estimation with normal measurement error with unknown variance., Statist. Sinica 16 195–211.
  • Meister, A. (2007). Deconvolving compactly supported densities., Math. Methods. Statist. 16 64–77.
  • Merritt, D. (1997). Recovering velocity distributions via penalized likelihood., Astronomical J. 114 228–237.
  • National Research Council, Committee on pesticides in the diets of infants and children (1993)., Pesticides in the Diets of Infants and Children. National Academies Press.
  • Neumann, M.H. (1997). On the effect of estimating the error density in nonparametric deconvolution., J. Nonparametr. Statist. 7 307–330.
  • Schennach, S. (2004). Nonparametric regression in the presence of measurement error., Econom. Theory 20 1046–1093.
  • Stefanski, L. and Bay, J.M. (1996). Simulation extrapolation deconvolution of finite population cumulative distribution function estimators., Biometrika 83 407–417.
  • Stefanski, L. and Carroll, R.J. (1990). Deconvoluting kernel density estimators., Statistics 21 169–184.
  • Zhang, S. and Karunamuni, R. (2000). Boundary bias correction for nonparametric deconvolution., Ann. Inst. Statist. Math. 52 612–629.