• Bernoulli
  • Volume 5, Number 2 (1999), 209-224.

Random-design regression under long-range dependent errors

Sándor Csörgö and Jan Mielniczuk

Full-text: Open access


We consider the random-design nonparametric regression model with long-range dependent errors that may also depend on the independent and identically distributed explanatory variables. Disclosing a smoothing dichotomy, we show that the finite-dimensional distributions of the Nadaraya-Watson kernel estimator of the regression function converge either to those of a degenerate process with completely dependent marginals or to those of a Gaussian white-noise process. The first case occurs when the bandwidths are large enough in a specified sense to allow long-range dependence to prevail. The second case is for bandwidths that are small in the given sense, when both the required norming sequence and the limiting process are the same as if the errors were independent. The borderline situation results in a limiting convolution of the two cases. The main results contrast with previous findings for deterministic-design regression.

Article information

Bernoulli, Volume 5, Number 2 (1999), 209-224.

First available in Project Euclid: 5 March 2007

Permanent link to this document

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

asymptotic finite-dimensional distributions kernel estimators long-range and short-range dependent errors random-design regression smoothing dichotomy


Csörgö, Sándor; Mielniczuk, Jan. Random-design regression under long-range dependent errors. Bernoulli 5 (1999), no. 2, 209--224.

Export citation


  • [1] Beran, J. (1992) Statistical methods for data with long-range dependence. Statist. Sci., 7, 404-427.
  • [2] Beran, J. (1994) Statistics for Long-memory Processes. London: Chapman & Hall.
  • [3] Castellana, J.V. and Leadbetter, M.R. (1986) On smoothed probability density estimation. Stochastic Processes Applic., 21, 179-193.
  • [4] Cheng, B. and Robinson, P.M. (1994) Semiparametric estimation from time series with long-range dependence. J. Econometrics, 64, 335-353.
  • [5] Csörgö, S. and Mielniczuk, J. (1995a) Density estimation under long-range dependence. Ann. Statist., 23, 990-999.
  • [6] Csörgö, S. and Mielniczuk, J. (1995b) Nonparametric regression under long-range dependent normal errors. Ann. Statist., 23, 1000-1014.
  • [7] Csörgö, S. and Mielniczuk, J. (1995c) Close short-range dependent sums and regression estimation. Acta Sci. Math. [Szeged], 60, 177-196.
  • [8] Csörgö, S. and Mielniczuk, J. (1995d) Distant long-range dependent sums and regression estimation. Stochastic Processes Applic., 56, 143-155
  • [9] Devroye, L.P. and Wagner, T.J. (1979) The L1-consistency of kernel density estimates. Ann. Statist., 7, 1136-1139.
  • [10] Dobrushin, R.L. and Major, P. (1979) Non-central limit theorems for non-linear functionals of Gaussian fields. Z. Wahrscheinlichkeitstheorie Verw. Geb., 50, 27-52.
  • [11] Giraitis, L., Koul, H.L. and Surgailis, D. (1994) Asymptotic normality of regression estimators with long memory errors. Statist. Probab. Lett., 29, 317-335.
  • [12] Giraitis, L. and Surgailis, D. (1985) CLT and other limit theorems for functionals of Gaussian processes. Z. Wahrscheinlichkeitstheorie Verw. Geb., 70, 191-212.
  • [13] Hall, P. and Hart, J.D. (1990a) Convergence rates in density estimation for data from infinite-order moving average processes. Probab. Theory Related Fields, 87, 253-274.
  • [14] Hall, P. and Hart, J.D. (1990b) Nonparametric regression with long-range dependence. Stochastic Processes Applic., 36, 339-351.
  • [15] Hall, P., Lahiri, S.N. and Polzehl, J. (1995a) On bandwidth choice in nonparametric regression with both short- and long-range dependent errors. Ann. Statist., 23, 1921-1936.
  • [16] Hall, P., Lahiri, S.N. and Truong, J.K. (1995b) On bandwidth choice for density estimation with dependent data. Ann. Statist., 23, 2241-2263.
  • [17] Ho, H.-C. (1996) On central and non-central limit theorems in density estimation for sequences of long-range dependence. Stochastic Processes Applic., 63, 153-174.
  • [18] Koul, H.L. (1992) M-estimators in linear models with long range dependent errors. Statist. Probab. Lett., 14, 153-164.
  • [19] Koul, H.L. and Mukherjee, K. (1993) Asymptotics of R-, MD- and LAD-estimators in linear regression models with long range dependent errors. Probab. Theory Related Fields, 95, 535-553.
  • [20] Nadaraya, E.A. (1964) Smooth regression analysis. Theory Probab. Applic., 9, 141-142.
  • [21] Robinson, P.M. (1994) Time series with strong dependence. In C.A. Sims (ed.), Advances in Econometrics. Sixth World Congress, Vol. 1, pp. 47-95. Cambridge: Cambridge University Press.
  • [22] Robinson, P.M. and Hidalgo, F.J. (1997) Time series regression with long range dependence. Ann. Statist., 25, 77-104.
  • [23] Rosenblatt, M. (1970) Density estimates and Markov sequences. In M.L. Puri (ed.), Nonparametric Techniques in Statistical Inference, pp. 199-210. Cambridge: Cambridge University Press.
  • [24] Schuster, E.F. (1972) Joint asymptotic distribution of the estimated regression function at a finite number of distinct points. Ann. Math. Statist., 43, 84-88.
  • [25] Taqqu, M.S. (1975) Weak convergence to fractional Brownian motion and to the Rosenblatt process. Z. Wahrscheinlichkeitstheorie Verw. Geb., 31, 287-302.
  • [26] Taqqu, M.S. (1979) Convergence of integrated processes of arbitrary Hermite rank. Z. Wahrscheinlichkeitstheorie Verw. Geb., 50, 53-83.
  • [27] Tobin, J. (1958) Estimation of relationships for limited dependent variables. Econometrica, 26, 24-36.
  • [28] Watson, G.S. (1964) On estimating regression. Sankhya A, 26, 359-372.