Asymptotic properties of $M$-estimators of parameters of a nonlinear regression model with a random noise whose spectrum is singular
Authors:
A. V. Ivanov and I. V. Orlovskyi
Translated by:
S. Kvasko
Journal:
Theor. Probability and Math. Statist. 93 (2016), 33-49
MSC (2010):
Primary 62J02; Secondary 62J99
DOI:
https://doi.org/10.1090/tpms/993
Published electronically:
February 7, 2017
MathSciNet review:
3553438
Full-text PDF Free Access
Abstract |
References |
Similar Articles |
Additional Information
Abstract: Time continuous nonlinear regression model with a noise being a nonlinearly transformed Gaussian stationary process with a singular spectrum is considered in the paper. Sufficient conditions for the asymptotic normality of the $M$-estimator are found for the vector parameter in this model.
References
- Peter J. Huber, Robust regression: asymptotics, conjectures and Monte Carlo, Ann. Statist. 1 (1973), 799–821. MR 356373
- Peter J. Huber, Robust statistics, Wiley Series in Probability and Mathematical Statistics, John Wiley & Sons, Inc., New York, 1981. MR 606374
- Frank R. Hampel, Elvezio M. Ronchetti, Peter J. Rousseeuw, and Werner A. Stahel, Robust statistics, Wiley Series in Probability and Mathematical Statistics: Probability and Mathematical Statistics, John Wiley & Sons, Inc., New York, 1986. The approach based on influence functions. MR 829458
- Hira L. Koul, $M$-estimators in linear models with long range dependent errors, Statist. Probab. Lett. 14 (1992), no. 2, 153–164. MR 1173413, DOI 10.1016/0167-7152(92)90079-K
- Hira L. Koul, Asymptotics of $M$-estimators in non-linear regression with long-range dependent errors, Athens Conference on Applied Probability and Time Series Analysis, Vol. II (1995), Lect. Notes Stat., vol. 115, Springer, New York, 1996, pp. 272–290. MR 1466752, DOI 10.1007/978-1-4612-2412-9_{2}0
- Hira L. Koul and Kanchan Mukherjee, Regression quantiles and related processes under long range dependent errors, J. Multivariate Anal. 51 (1994), no. 2, 318–337. MR 1321301, DOI 10.1006/jmva.1994.1065
- Liudas Giraitis, Hira L. Koul, and Donatas Surgailis, Asymptotic normality of regression estimators with long memory errors, Statist. Probab. Lett. 29 (1996), no. 4, 317–335. MR 1409327, DOI 10.1016/0167-7152(95)00188-3
- Hira L. Koul and Donatas Surgailis, Asymptotic expansion of $M$-estimators with long-memory errors, Ann. Statist. 25 (1997), no. 2, 818–850. MR 1439325, DOI 10.1214/aos/1031833675
- Hira L. Koul and Donatas Surgailis, Second-order behavior of $M$-estimators in linear regression with long-memory errors, J. Statist. Plann. Inference 91 (2000), no. 2, 399–412. Prague Workshop on Perspectives in Modern Statistical Inference: Parametrics, Semi-parametrics, Non-parametrics (1998). MR 1814792, DOI 10.1016/S0378-3758(00)00190-7
- H. L. Koul and D. Surgailis, Robust estimators in regression models with long memory errors, Theory and applications of long-range dependence, Birkhäuser Boston, Boston, MA, 2003, pp. 339–353. MR 1957498
- Liudas Giraitis, Hira L. Koul, and Donatas Surgailis, Asymptotic normality of regression estimators with long memory errors, Statist. Probab. Lett. 29 (1996), no. 4, 317–335. MR 1409327, DOI 10.1016/0167-7152(95)00188-3
- Hira L. Koul, Richard T. Baillie, and Donatas Surgailis, Regression model fitting with a long memory covariate process, Econometric Theory 20 (2004), no. 3, 485–512. MR 2061725, DOI 10.1017/S0266466604203036
- A. V. Ivanov and N. N. Leonenko, Asymptotic behavior of $M$-estimators in continuous-time non-linear regression with long-range dependent errors, Random Oper. Stochastic Equations 10 (2002), no. 3, 201–222. MR 1923424, DOI 10.1515/rose.2002.10.3.201
- A. Ivanov and N. Leonenko, Robust estimators in non-linear regression models with long-range dependence, Optimal design and related areas in optimization and statistics, Springer Optim. Appl., vol. 28, Springer, New York, 2009, pp. 193–221. MR 2513352, DOI 10.1007/978-0-387-79936-0_{9}
- Alexander V. Ivanov, Asymptotic properties of $L_p$-estimators, Theory Stoch. Process. 14 (2008), no. 1, 60–68. MR 2479706
- A. V. Ivanov and I. V. Orlovsky, L$_p$-estimates in nonlinear regression with long-range dependence, Theory Stoch. Process. 7(23) (2002), no. 3–4, 38–49.
- A. V. Ivanov and I. V. Orlovskyi, Consistency of $M$-estimators in nonlinear regression models with continuous time, Naukovi visti NTUU “KPI” 4(42) (2005), 140–147. (Ukrainian)
- A. V. Ivanov and I. V. Orlovskyi, The uniqueness of $M$-estimators of parameters in nonlinear regression models, Naukovi Visti NTUU “KPI” 4(66) (2009), 135–141. (Ukrainian)
- Ī. M. Savich, Consistency of quantile estimators in regression models with long-range dependent noise, Teor. Ĭmovīr. Mat. Stat. 82 (2010), 128–136 (Ukrainian, with English, Russian and Ukrainian summaries); English transl., Theory Probab. Math. Statist. 82 (2011), 129–138. MR 2790488, DOI 10.1090/S0094-9000-2011-00832-0
- Igor V. Orlovsky, $M$-estimates in nonlinear regression with weak dependence, Theory Stoch. Process. 9 (2003), no. 1-2, 108–122. MR 2080017
- Alexander Ivanov and Igor V. Orlovsky, Consistency of $M$-estimates in general nonlinear regression models, Theory Stoch. Process. 13 (2007), no. 1-2, 86–97. MR 2343813
- I. V. Orlovsky, Asymptotic properties of $M$-estimators of parameters in nonlinear regression models, Abstract of candidate thesis (Physics and Mathematics), Kyiv National Taras Shevchenko University, Kyiv, 2007. (Ukrainian)
- Alexander V. Ivanov, Nikolai Leonenko, María D. Ruiz-Medina, and Irina N. Savich, Limit theorems for weighted nonlinear transformations of Gaussian stationary processes with singular spectra, Ann. Probab. 41 (2013), no. 2, 1088–1114. MR 3077537, DOI 10.1214/12-AOP775
- Yu. V. Goncharenko and S. I. Lyashko, Brouwer’s Theorem, “KIĬ”, Kiev, 2000. (Russian)
- V. V. Anh, V. P. Knopova, and N. N. Leonenko, Continuous-time stochastic processes with cyclical long-range dependence, Aust. N. Z. J. Stat. 46 (2004), no. 2, 275–296. MR 2076396, DOI 10.1111/j.1467-842X.2004.00329.x
- A. V. Ivanov, N. N. Leonenko, M. D. Ruiz-Medina, and B. M. Zhurakovsky, Estimation of harmonic component in regression with cyclically dependent errors, Statistics 49 (2015), no. 1, 156–186. MR 3304373, DOI 10.1080/02331888.2013.864656
- Ulf Grenander, On the estimation of regression coefficients in the case of an autocorrelated disturbance, Ann. Math. Statistics 25 (1954), 252–272. MR 62402, DOI 10.1214/aoms/1177728784
- Il′dar Abdullovich Ibragimov and Y. A. Rozanov, Gaussian random processes, Applications of Mathematics, vol. 9, Springer-Verlag, New York-Berlin, 1978. Translated from the Russian by A. B. Aries. MR 543837
- Patrick Billingsley, Convergence of probability measures, John Wiley & Sons, Inc., New York-London-Sydney, 1968. MR 0233396
- A. V. Ivanov and I. M. Savych, The $\mu$-admissibility of a spectral density for long range dependent random noise in nonlinear regression models, Naukovi visti NTUU “KPI” 1 (2009), 143–148. (Ukrainian)
- N. N. Leonenko and A. V. Ivanov, Statistical Analysis of Random Fields, “Vyshcha Shkola”, Kiev, 1986; English transl., Kluwer Academic Publishers Group, Dordrecht, 1989.
- R. N. Bhattacharya and R. Ranga Rao, Normal Approximation and Asymptotic Expansions, John Wiley & Sons, New York–London–Sydney, 1976.
- J. H. Wilkinson, The Algebraic Eigen Value Problem, Clarendon Press, Oxford, 1962.
References
- P. J. Huber, Robust regression: asymptotics, conjectures and Monte-Carlo, Ann. Statist. 1 (1973), no. 5, 799–821. MR 0356373
- P. J. Huber, Robust Statistics, John Wiley & Sons, Inc., New York, 1981. MR 606374
- F. R. Hampel, E. M. Ronchetti, P. J. Rousseeuw, and W. A. Stahel, Robust Statistics. The Approach Based on Influence Functions, Wiley, New York, 1986. MR 829458
- H. L. Koul, $M$-estimators in linear models with long range dependent errors, Stat. Probab. Lett. 14 (1992), 153–164. MR 1173413
- H. L. Koul, Asymptotics of $M$-estimations in non-linear regression with long-range dependence errors, Proc. Athens Conf. Appl. Probabl. and Time Ser. Analysis (P. M. Robinson and M. Rosenblatt, eds.), Springer-Verlag Lecture Notes in Statistics, vol. II, 1996, pp. 272–291. MR 1466752
- H. L. Koul and K. Mukherjee, Regression quantiles and related processes under long range dependent errors, J. Multiv. Anal. 51 (1994), 318–337. MR 1321301
- L. Giraitis, H. L. Koul, and D. Surgailis, Asymptotic normality of regression estimators with long memory errors, Stat. Probab. Lett. 29 (1996), 317–335. MR 1409327
- H. L. Koul and D. Surgailis, Asymptotic expansion of $M$-estimators with long memory errors, Ann. Statist. 25 (1997), 818–850. MR 1439325
- H. L. Koul and D. Surgailis, Second order behavior of $M$-estimators in linear regression with long-memory errors, J. Statist. Plann. Inference 91 (2000), 399–412. MR 1814792
- H. L. Koul and D. Surgailis, Robust estimators in regression models with long memory errors, Theory and Application of Long-Range Dependence (P. Doukhan, G. Pantheism, and M. S. Taqqu, eds.), Birkhäuser, Boston, 2003, pp. 339–353. MR 1957498
- L. Giraitis and H. L. Koul, Estimation of the dependence parameter in linear regression with long-range dependent errors, Stat. Probab. Lett. 29 (1996), 317–335. MR 1409327
- R. T. Baillie, H. L. Koul, and D. Surgailis, Regression model fitting with a long memory covariance process, Economic Theory 20 (2004), 485–512. MR 2061725
- A. V. Ivanov and N. N. Leonenko, Asymptotic behavior of $M$-estimators in continuous-time non-linear regression with long-range dependent errors, Random Oper. Stoch. Equ. 10 (2002), no. 3, 201–222. MR 1923424
- A. V. Ivanov and N. N. Leonenko, Robust estimators in nonlinear regression models with long-range dependence, Optimal Design and Related Areas in Optimization and Statistics (L. Pronzato and A. Zhigljavsky, eds.), Springer, Berlin, 2009, pp. 193–221. MR 2513352
- A. V. Ivanov, Asymptotic properties of $L_p$-estimators, Theory Stoch. Process. 14(30) (2008), no. 1, 60–68. MR 2479706
- A. V. Ivanov and I. V. Orlovsky, L$_p$-estimates in nonlinear regression with long-range dependence, Theory Stoch. Process. 7(23) (2002), no. 3–4, 38–49.
- A. V. Ivanov and I. V. Orlovskyi, Consistency of $M$-estimators in nonlinear regression models with continuous time, Naukovi visti NTUU “KPI” 4(42) (2005), 140–147. (Ukrainian)
- A. V. Ivanov and I. V. Orlovskyi, The uniqueness of $M$-estimators of parameters in nonlinear regression models, Naukovi Visti NTUU “KPI” 4(66) (2009), 135–141. (Ukrainian)
- I. N. Savych, Consistency of quantile estimators in regression models with long-range dependent noise, Teor. Ĭmovir. Mat. Stat. translation in 82 (2010), 128–136; English transl. in Theory Probab. Math. Statist. 82 (2011), 129–138. MR 2790488
- I. V. Orlovsky, $M$-estimates in nonlinear regression with weak dependence, Theory Stoch. Process. 9(25) (2003), no. 1–2, 108–122. MR 2080017
- A. V. Ivanov and I. V. Orlovsky, Consistency of M-estimates in general nonlinear model, Theory Stoch. Process. 13(29) (2007), no. 1–2, 86–97. MR 2343813
- I. V. Orlovsky, Asymptotic properties of $M$-estimators of parameters in nonlinear regression models, Abstract of candidate thesis (Physics and Mathematics), Kyiv National Taras Shevchenko University, Kyiv, 2007. (Ukrainian)
- A. V. Ivanov, N. N. Leonenko, M. D. Ruiz-Medina, and I. N. Savych, Limit theorems for weighted non-linear transformations of Gaussian processes with singular spectra, Ann. Probab. 41 (2013), no. 2, 1088–1114. MR 3077537
- Yu. V. Goncharenko and S. I. Lyashko, Brouwer’s Theorem, “KIĬ”, Kiev, 2000. (Russian)
- V. V. Anh, V. P. Knopova, and N. N. Leonenko, Continuous-time stochastic processes with cyclical long-range dependence, Aust. NZ J. Stat. 46 (2004), 275–296. MR 2076396
- A. V. Ivanov, N. N. Leonenko, M. D. Ruiz-Medina, B. M. Zhurakovsky, Estimation of harmonic component in regression with cyclically dependent errors, Statistics: A Journal of Theoretical and Applied Statistics, 49 (2015), no. 1, 156–186. MR 3304373
- U. Grenander, On the estimation of regression coefficients in the case of an autocorrelated disturbance, Ann. Statist 25 (1954), no. 2, 252–272. MR 0062402
- I. A. Ibragimov and Yu. A. Rozanov, Gaussian Random Processes, “Nauka”, Moscow, 1970; English transl. Springer-Verlag, New York–Berlin, 1978. MR 543837
- P. Billingsley, Convergence of probability measures, John Wiley & Sons, Inc., New York–London–Sydney, 1968. MR 0233396
- A. V. Ivanov and I. M. Savych, The $\mu$-admissibility of a spectral density for long range dependent random noise in nonlinear regression models, Naukovi visti NTUU “KPI” 1 (2009), 143–148. (Ukrainian)
- N. N. Leonenko and A. V. Ivanov, Statistical Analysis of Random Fields, “Vyshcha Shkola”, Kiev, 1986; English transl., Kluwer Academic Publishers Group, Dordrecht, 1989.
- R. N. Bhattacharya and R. Ranga Rao, Normal Approximation and Asymptotic Expansions, John Wiley & Sons, New York–London–Sydney, 1976.
- J. H. Wilkinson, The Algebraic Eigen Value Problem, Clarendon Press, Oxford, 1962.
Similar Articles
Retrieve articles in Theory of Probability and Mathematical Statistics
with MSC (2010):
62J02,
62J99
Retrieve articles in all journals
with MSC (2010):
62J02,
62J99
Additional Information
A. V. Ivanov
Affiliation:
Department of Mathematical Analysis and Probability Theory, National Technical University of Ukraine “KPI”, Peremogy Avenue, 37, Kyiv 03056, Ukraine
Email:
alexntuu@gmail.com
I. V. Orlovskyi
Affiliation:
Department of Mathematical Analysis and Probability Theory, National Technical University of Ukraine “KPI”, Peremogy Avenue, 37, Kyiv 03056, Ukraine
Email:
i.v.orlovsky@gmail.com
Keywords:
Asymptotic uniqueness of an estimator,
asymptotic normality,
$M$-estimators,
nonlinear regression models,
singular spectrum
Received by editor(s):
August 5, 2015
Published electronically:
February 7, 2017
Additional Notes:
The paper was prepared following the talk at the International Conference “Probability, Reliability and Stochastic Optimization (PRESTO-2015)” held in Kyiv, Ukraine, April 7–10, 2015
Article copyright:
© Copyright 2017
American Mathematical Society