Kybernetika 59 no. 1, 1-27, 2023

Complete f-moment convergence for weighted sums of WOD arrays with statistical applications

Xi Chen, Xinran Tao and Xuejun WangDOI: 10.14736/kyb-2023-1-0001

Abstract:

Complete $f$-moment convergence is much more general than complete convergence and complete moment convergence. In this work, we mainly investigate the complete $f$-moment convergence for weighted sums of widely orthant dependent (WOD, for short) arrays. A general result on Complete $f$-moment convergence is obtained under some suitable conditions, which generalizes the corresponding one in the literature. As an application, we establish the complete consistency for the weighted linear estimator in nonparametric regression models. Finally, some simulations are provided to show the numerical performance of theoretical results based on finite samples.

Keywords:

complete convergence, weighted sums, widely orthant dependent arrays, complete $f$-moment convergence, nonparametric regression models, complete consistency

Classification:

60F15, 62G20

paper.pdf

References:

  1. A. Adler and A. Rosalsky: Some general strong laws for weighted sums of stochastically dominated random variables. Stoch. Anal. Appl. 5 (1987), 1-16.   DOI:10.1080/07362998708809104
  2. A. Adler, A. Rosalsky and R. L. Taylor: Strong laws of large numbers for weighted sums of random elements in normed linear spaces. Int. J. Math. Math. Sci. 12 (1989), 507-530.   CrossRef
  3. P. Y. Chen and S. H. Sung: A Spitzer-type law of large numbers for widely orthant dependent random variables. Statist. Probab. Lett. 2054 (2019), 1-8, Article ID 108544.   DOI:10.1016/j.spl.2019.06.020
  4. Y. S. Chow: On the rate of moment convergence of sample sums and extremes. Bull. Inst. Math., Academia Sinica 16 (1988), 177-201.   CrossRef
  5. A. A. Georgiev: Local properties of function fitting estimates with applications to system identification. In: Mathematics Statistics and Applications. Proceedings 4th Pannonian Symposium on Mathematical Statistics 1983, (W. Grossmann, ed.). vol. B, Bad Tatzmannsdorf, Austria, Reidel, Dordrecht, pp. 141-51.   CrossRef
  6. A. A. Georgiev and W. Greblicki: Nonparametric function recovering from noisy observations. J. Statist. Plann. Inference 13 (1986), 1-14.   DOI:10.1016/0378-3758(86)90114-X
  7. Q. H. He: Consistency of the Priestley-Chao estimator in nonparametric regression model with widely orthant dependent errors. J. Inequal. Appl. 2019 (2019), 1-13, Article ID 64.   DOI:10.1186/s13660-019-2016-8
  8. P. L. Hsu and H. Robbins: Complete convergence and the law of large numbers. Proc. National Acad. Sci. Unit. States Amer. 33 (1947), 25-31.   DOI:10.1073/pnas.33.2.25
  9. K. Joag-Dev and F. Proschan: Negative association of random variables with applications. Ann. Statist. 11 (1983), 286-295.   DOI:10.1214/aos/1176346079
  10. J. J. Lang, T. Y. He, L. Cheng, C. Lu and X. J. Wang: Complete convergence for weighted sums of widely orthant-dependent random variables and its statistical application. Revista Mat. Complut. 34 (2021), 853-881.   DOI:10.1007/s13163-020-00369-5
  11. Y. M. Li, Y. Zhou and C. Liu: On the convergence rates of kernel estimator and hazard estimator for widely dependent samples. J. Inequal. Appl. 2018 (2018), 1-10, Article ID 71.   DOI:10.1186/s13660-018-1659-1
  12. H. Y. Liang and B. Y. Jing: Asymptotic properties for estimates of nonparametric regression models based on negatively associated sequences. J. Multivar. Anal. 95 (2005), 227-245.   DOI:10.1016/j.jmva.2004.06.004
  13. H. Y. Liang and J. J. Zhang: Strong convergence for weighted sums of negatively associated arrays. Chinese Annals of Mathematics 31B (2010), 273-288.   DOI:10.1007/s11401-008-0016-y
  14. C. Lu, Z. Chen and X. J. Wang: Complete $f$-moment convergence for widely orthant dependent random variables and its application in nonparametric models. Acta Math. Sinica, English Series 35 (2019), 1917-1936.   DOI:10.1007/s10114-019-8315-7
  15. D. H. Qiu abd T. C. Hu: Strong limit theorems for weighted sums of widely orthant dependent random variables. J. Math. Res. Appl. 34 (2014), 105-113.   CrossRef
  16. D. H. Qiu and P. Y. Chen: Complete and complete moment convergence for weighted sums of widely orthant dependent random variables. Acta Math. Sinica, English Series 30 (2014), 1539-1548.   DOI:10.1007/s10114-014-3483-y
  17. G. G. Roussas, L. T. Tran and D. A. Ioannides: Fixed design regression for time series: asymptotic. J. Multivar. Anal. 40 (1992), 262-291.   DOI:10.1016/0047-259X(92)90026-C
  18. A.T. Shen: Complete convergence for weighted sums of END random variables and its application to nonparametric regression models. J. Nonparametr. Statist. 28 (2016), 702-715.   DOI:10.1080/10485252.2016.1225050
  19. A. T. Shen and C. Q. Wu: Complete $q$th moment convergence and its statistical applications. RACSAM 114 (2019), 1-25, Article ID 35.   CrossRef
  20. A. T. Shen, M. Yao, W. J. Wang and A. Volodin: Exponential probability inequalities for WNOD random variables and their applications. RACSAM 110 (2016), 251-268.   DOI:10.1007/s13398-015-0233-7
  21. A. T. Shen and S. Y. Zhang: On complete consistency for the estimator of nonparametric regression model based on asymptotically almost negatively associated errors. Methodol. Comput. Appl. Probab. 23 (2021), 1285-1307.   DOI:10.1007/s11009-020-09813-x
  22. A. T. Shen, Y. Zhang and A. Volodin: Applications of the Rosenthal-type inequality for negatively super-additive dependent random variables. Metrika 78 (2015), 295-311.   DOI:10.1007/s00184-014-0503-y
  23. W. F. Stout: Almost Sure Convergence. Academic Press, New York 1974.   CrossRef
  24. C. J. Stone: Consistent nonparametric regression regression. Ann. Statist. 5 (1977), 595-620.   CrossRef
  25. L. Tran, G. Roussas, S. Yakowitz and V. B. Truong: Fixed design regression for linear time series. Ann. Statist. 24 (1996), 975-991.   DOI:10.1214/aos/1032526952
  26. Y. Wang and X. J. Wang: Complete $f$-moment convergence for Sung's type weighted sums and its application to the EV regression models. Statist. Papers 62 (2021), 769-793.   DOI:10.1007/s00362-019-01112-z
  27. K. Y. Wang, Y. B. Wang and Q. W. Gao: Uniform asymptotics for the finite-time ruin probability of a dependent risk model with a constant interest rate. Methodol. Comput. Appl. Probab. 15 (2013), 109-124.   DOI:10.1007/s11009-011-9226-y
  28. M. M. Xi, R. Wang, Z. Y. Cheng and X. J. Wang: Some convergence properties for partial sums of widely orthant dependent random variables and their statistical applications. Statist. Papers 61 (2020), 1663-1684.   DOI:10.1007/s00362-018-0996-y
  29. Q. Y. Wu: Probability Limit Theory for Mixing Sequences. Science Press of China, Beijing 2006.   CrossRef
  30. Y. Wu, X. J. Wang and S. H. Hu: Complete moment convergence for weighted sums of weakly dependent random variables and its application in nonparametric regression model. Statist. Probab. Lett. 127 (2017), 56-66.   DOI:10.1016/j.spl.2017.03.027
  31. Y. Wu, X. J. Wang, T. C. Hu and A. Volodin: Complete $f$-moment convergence for extended negatively dependent random variables. RACSAM 113 (2019), 333-351.   CrossRef
  32. Y. Wu, X. J. Wang and A. Rosalsky: Complete moment convergence for arrays of rowwise widely orthant dependent random variables. Acta Math. Sinica, English Series 34 (2018), 1531-1548.   DOI:10.1007/s10114-018-7173-z
  33. Y. Wu, X. J. Wang and A. T. Shen: Strong convergence properties for weighted sums of m-asymptotic negatively associated random variables and statistical applications. Statist. Papers 62 (2021), 2169-94.   DOI:10.1007/s00362-020-01179-z
  34. W. Z. Yang, H. Y. Xu, L. Chen and aand S. H. Hu: Complete consistency of estimators for regression models based on extended negatively dependent. Statist. Papers 59 (2018), 449-465.   DOI:10.1137/17N974355
  35. S. L. Zhang, C. Qu and T. T. Hou: Limit behaviors of the estimator of nonpar ametric regression model based on extended negatively dependent errors. Commun. Statist. - Theory Methods, 2022, in press.   DOI:10.1080/03610926.2022.2069263
  36. X. C. Zhou, J. G. Lin and C. M. Yin: Asymptotic properties of wavelet-based estimator in nonparametric regression model with weakly dependent processes. J. Inequal. Appl. 2013 (2013), 1-18, Article ID 261.   DOI:10.1186/1029-242x-2013-261
  37. X. J. Wang, C. Xu, T. C. Hu, A. Volodin and S. H. Hu: On complete convergence for widely orthant-dependent random variables and its applications in nonparametric regression models. TEST 23 (2014), 607-629.   DOI:10.1007/s11749-014-0365-7