The Annals of Statistics

Wavelet regression in random design with heteroscedastic dependent errors

Rafał Kulik and Marc Raimondo

Full-text: Open access

Enhanced PDF (336 KB)

Abstract

We investigate function estimation in nonparametric regression models with random design and heteroscedastic correlated noise. Adaptive properties of warped wavelet nonlinear approximations are studied over a wide range of Besov scales, $f\in\mathcal{B}_{\pi,r}^{s}$, and for a variety of Lp error measures. We consider error distributions with Long-Range-Dependence parameter α, 0<α≤1; heteroscedasticity is modeled with a design dependent function σ. We prescribe a tuning paradigm, under which warped wavelet estimation achieves partial or full adaptivity results with the rates that are shown to be the minimax rates of convergence. For p>2, it is seen that there are three rate phases, namely the dense, sparse and long range dependence phase, depending on the relative values of s, p, π and α. Furthermore, we show that long range dependence does not come into play for shape estimation f−∫f. The theory is illustrated with some numerical examples.

Article information

Source
Ann. Statist., Volume 37, Number 6A (2009), 3396-3430.

Dates
First available in Project Euclid: 17 August 2009

Permanent link to this document
https://projecteuclid.org/euclid.aos/1250515391

Digital Object Identifier
doi:10.1214/09-AOS684

Mathematical Reviews number (MathSciNet)
MR2549564

Zentralblatt MATH identifier
1369.62074

Subjects
Primary: 62G05: Estimation
Secondary: 62G08: Nonparametric regression 62G20: Asymptotic properties

Keywords
Adaptive estimation nonparametric regression shape estimation random design long range dependence wavelets thresholding maxiset warped wavelets

Citation

Kulik, Rafał; Raimondo, Marc. Wavelet regression in random design with heteroscedastic dependent errors. Ann. Statist. 37 (2009), no. 6A, 3396--3430. doi:10.1214/09-AOS684. https://projecteuclid.org/euclid.aos/1250515391


Export citation

References

  • [1] Beran, J. and Feng, Y. (2001). Local polynomial estimation with a FARIMA–GARCH error process. Bernoulli 7 733–750.
    Mathematical Reviews (MathSciNet): MR1867080
    Digital Object Identifier: doi:10.2307/3318539
    Project Euclid: euclid.bj/1079399539
  • [2] Beran, J. and Feng, Y. (2002). Local polynomial fitting with long-memory, short-memory and antipersistent errors. Ann. Inst. Statist. Math. 54 291–311.
    Mathematical Reviews (MathSciNet): MR1910174
    Zentralblatt MATH: 1012.62033
    Digital Object Identifier: doi:10.1023/A:1022469818068
  • [3] Cai, T. and Brown, L. D. (1999). Wavelet estimation for samples with random uniform design. Statist. Probab. Lett. 42 313–321.
    Mathematical Reviews (MathSciNet): MR1688134
  • [4] Cheng, B. and Robinson, P. M. (1991). Density estimation in strongly dependent nonlinear time series. Statist. Sinica 1 335–359.
    Mathematical Reviews (MathSciNet): MR1130123
    Zentralblatt MATH: 0823.62031
  • [5] Cheng, B. and Robinson, P. M. (1994). Semiparametric estimation from time series with long-range dependence. J. Econometrics 64 335–353.
    Mathematical Reviews (MathSciNet): MR1310526
    Zentralblatt MATH: 0808.62081
    Digital Object Identifier: doi:10.1016/0304-4076(94)90068-X
  • [6] Claeskens, G. and Hall, P. (2002). Effect of dependence on stochastic measures of accuracy of density estimators. Ann. Statist. 30 431–454.
    Mathematical Reviews (MathSciNet): MR1902894
    Zentralblatt MATH: 1012.62031
    Digital Object Identifier: doi:10.1214/aos/1021379860
    Project Euclid: euclid.aos/1021379860
  • [7] Cohen, A., Daubechies, I. and Vial, P. (1993). Wavelets on the interval and fast wavelet transforms. Appl. Comput. Harmon. Anal. 1 54–81.
    Mathematical Reviews (MathSciNet): MR1256527
    Digital Object Identifier: doi:10.1006/acha.1993.1005
  • [8] Csörgő, S. and Mielniczuk, J. (1999). Random-design regression under long-range dependent errors. Bernoulli 5 209–224.
    Mathematical Reviews (MathSciNet): MR1681695
    Digital Object Identifier: doi:10.2307/3318432
    Project Euclid: euclid.bj/1173147903
  • [9] Csörgő, S. and Mielniczuk, J. (2000). The smoothing dichotomy in random-design regression with long-memory errors based on moving averages. Statist. Sinica 10 771–787.
    Mathematical Reviews (MathSciNet): MR1787779
    Zentralblatt MATH: 1053.62553
  • [10] Donoho, D., Johnstone, I. M., Kerkyacharian, G. and Picard, D. (1996). Density estimation by wavelet thresholding. Ann. Statist. 24 508–539.
    Mathematical Reviews (MathSciNet): MR1394974
    Zentralblatt MATH: 0860.62032
    Digital Object Identifier: doi:10.1214/aos/1032894451
    Project Euclid: euclid.aos/1032894451
  • [11] Dzhaparidze, K. and van Zanten, J. H. (2001). On Bernstein-type inequalities for martingales. Stochastic Process. Appl. 93 109–117.
    Mathematical Reviews (MathSciNet): MR1819486
    Zentralblatt MATH: 1051.60022
    Digital Object Identifier: doi:10.1016/S0304-4149(00)00086-7
  • [12] Efromovich, S. (1999). How to overcome the curse of long-memory errors. IEEE Trans. Inform. Theory 45 1735–1741.
    Mathematical Reviews (MathSciNet): MR1699909
    Digital Object Identifier: doi:10.1109/18.771257
  • [13] Guo, H. and Koul, H. L. (2008). Asymptotic inference in some hetereoscedastic regression models with long memory design and errors. Ann. Statist. 36 458–487.
    Mathematical Reviews (MathSciNet): MR2387980
    Zentralblatt MATH: 1132.62066
    Digital Object Identifier: doi:10.1214/009053607000000686
    Project Euclid: euclid.aos/1201877310
  • [14] Hall, P. and Heyde, C. C. (1980). Martingale Limit Theory and Its Application. Academic Press, New York.
    Mathematical Reviews (MathSciNet): MR624435
    Zentralblatt MATH: 0462.60045
  • [15] Hall, P., Lahiri, S. N. and Truong, Y. K. (1995). On bandwidth choice for density estimation with dependent data. Ann. Statist. 23 2241–2263.
    Mathematical Reviews (MathSciNet): MR1389873
    Zentralblatt MATH: 0854.62039
    Digital Object Identifier: doi:10.1214/aos/1034713655
    Project Euclid: euclid.aos/1034713655
  • [16] Härdle, W., Kerkyacharian, G., Picard, D. and Tsybakov, A. (1997). Wavelets, Approximation, and Statistical Applications. Lecture Notes in Statistics 129. Springer, New York.
    Mathematical Reviews (MathSciNet): MR1618204
  • [17] Johnstone, I. M. (1999). Wavelet shrinkage for correlated data and inverse problems: Adaptivity results. Statist. Sinica 9 51–83.
    Mathematical Reviews (MathSciNet): MR1678881
    Zentralblatt MATH: 1065.62519
  • [18] Kerkyacharian, G. and Picard, D. (2000). Thresholding algorithms, maxisets and well-concentrated bases. Test 9 283–344.
    Mathematical Reviews (MathSciNet): MR1821645
    Zentralblatt MATH: 1107.62323
    Digital Object Identifier: doi:10.1007/BF02595738
  • [19] Kerkyacharian, G. and Picard, D. (2004). Regression in random design and warped wavelets. Bernoulli 10 1053–1105.
    Mathematical Reviews (MathSciNet): MR2108043
    Digital Object Identifier: doi:10.3150/bj/1106314850
    Project Euclid: euclid.bj/1106314850
  • [20] Kulik, R. and Raimondo, M. (2009). Lp wavelet regression with correlated errors. Statist. Sinica. To appear.
    Mathematical Reviews (MathSciNet): MR2589193
    Zentralblatt MATH: 05629269
  • [21] Mallat, S. (1998). A Wavelet Tour of Signal Processing, 2nd ed. Academic Press, San Diego, CA.
    Mathematical Reviews (MathSciNet): MR1614527
  • [22] Masry, E. (2001). Local linear regression estimation under long-range dependence: Strong consistency and rates. IEEE Trans. Inform. Theory 47 2863–2875.
    Mathematical Reviews (MathSciNet): MR1872846
    Digital Object Identifier: doi:10.1109/18.959266
  • [23] Masry, E. and Mielniczuk, J. (1999). Local linear regression estimation for time series with long-range dependence. Stochastic Process. Appl. 82 173–193.
    Mathematical Reviews (MathSciNet): MR1700004
    Zentralblatt MATH: 0991.62024
    Digital Object Identifier: doi:10.1016/S0304-4149(99)00015-0
  • [24] Mielniczuk, J. and Wu, W. B. (2004). On random-design model with dependent errors. Statist. Sinica 14 1105–1126.
    Mathematical Reviews (MathSciNet): MR2126343
    Zentralblatt MATH: 1060.62046
  • [25] Pensky, M. and Sapatinas, T. (2009). Functional deconvolution in a periodic setting: Uniform case. Ann. Statist. 37 73–104.
    Mathematical Reviews (MathSciNet): MR2488345
    Zentralblatt MATH: 05518688
    Digital Object Identifier: doi:10.1214/07-AOS552
    Project Euclid: euclid.aos/1232115928
  • [26] Robinson, P. M. and Hidalgo, F. J. (1997). Time series regression with long-range dependence. Ann. Statist. 25 77–104.
    Mathematical Reviews (MathSciNet): MR1429918
    Digital Object Identifier: doi:10.1214/aos/1069362387
    Project Euclid: euclid.aos/1034276622
  • [27] Wang, Y. (1996). Function estimation via wavelet shrinkage for long-memory data. Ann. Statist. 24 466–484.
    Mathematical Reviews (MathSciNet): MR1394972
    Zentralblatt MATH: 0859.62042
    Digital Object Identifier: doi:10.1214/aos/1032894449
    Project Euclid: euclid.aos/1032894449
  • [28] Wu, W. B. and Mielniczuk, J. (2002). Kernel density estimation for linear processes. Ann. Statist. 30 1441–1459.
    Mathematical Reviews (MathSciNet): MR1936325
    Zentralblatt MATH: 1015.62034
    Digital Object Identifier: doi:10.1214/aos/1035844982
    Project Euclid: euclid.aos/1035844982
  • [29] Yang, Y. (2001). Nonparametric regression with dependent errors. Bernoulli 7 633–655.
    Mathematical Reviews (MathSciNet): MR1849372
    Digital Object Identifier: doi:10.2307/3318730
    Project Euclid: euclid.bj/1079559467
  • [30] Yao, Q. and Tong, H. (1998). Cross-validatory bandwidth selections for regression estimation based on dependent data. J. Statist. Plann. Inference 68 387–415.
    Mathematical Reviews (MathSciNet): MR1629607
    Zentralblatt MATH: 0942.62046
    Digital Object Identifier: doi:10.1016/S0378-3758(97)00151-1

The Institute of Mathematical Statistics

The Annals of Statistics

New content alerts

Email RSS ToC RSS Article
  • You have access to this content.
  • You have partial access to this content.
  • You do not have access to this content.
Turn Off MathJax

What is MathJax?

More like this

+ See more