# [1]贺传富.非线性约束条件的平稳自回归模型的L1-估计[J].东南大学学报(自然科学版),2001,31(5):115-120.[doi:10.3969/j.issn.1001-0505.2001.05.025] 　He Chuanfu.L1-Estimators of Stationary Autoregressive Model with Nonlinear Constraints[J].Journal of Southeast University (Natural Science Edition),2001,31(5):115-120.[doi:10.3969/j.issn.1001-0505.2001.05.025] 点击复制 非线性约束条件的平稳自回归模型的L1-估计() 分享到： var jiathis_config = { data_track_clickback: true };

31

2001年第5期

115-120

2001-09-20

## 文章信息/Info

Title:
L1-Estimators of Stationary Autoregressive Model with Nonlinear Constraints

Author(s):
He Chuanfu
Department of Mathematics, Nanjing University, Nanjing 210093, China)

Keywords:

O211.61
DOI:
10.3969/j.issn.1001-0505.2001.05.025

L1-估计是统计问题中一个重要估计.时间序列模型的L1-估计问题是非常重要的,这些估计量的多种性质都被研究过.许多统计学者讨论了它在无约束条件情况下的估计问题及其有关性质,且得到了很好的结果,然而,仍有一些基本问题有待解决.本文讨论了平稳自回归模型的L1-估计在非线性约束条件下的渐近性质.该约束条件是由非线性等式和不等式给出.这种估计问题属于随机优化问题.用最优化的方法克服非线性约束问题在估计研究上的困难,为估计提供一个新的途径,并得到了L1-估计问题的相关结果.
Abstract:
L1-estimator is an important estimator in statistic problems. L1-estimation for time series is very important. Some properties of these estimators have been studied. Many statistics scholars have studied estimator problems and their properties with absence of restriction and reached good conclusions. However, some basic problems on this subject are left open. This paper studies the asymptotic behavior of L1-estimator of stationary autoregressive models with nonlinear constraint. Here the constraint is given by nonlinear equalities and inequalities. This kind of estimation problem is a stochastic optimization problem. Optimization methods are used to overcome the difficulty caused by nonlinear constraint and this paper also provides relevant conclusions of this problem.

## 参考文献/References:

[1] Franke J,Hardle W,Martin D.Robust and nonlinear time series analysis.Berlin:Springer-verlag,1984.124～137
[2] Martin D.Robust methods for times series.New York:Academic Press,1981.230～249
[3] Basset G,Koenker R.Asymptotic theory of least abstract error regressions.J America Statistical Association,1978,73(6):618～622
[4] Rao C R.Methodology based on the L1-norm in statistical inferences.Sankhya Series A,1988,50(3):289～313
[5] Bai Z D,Chen X R,Wu Y H,et al.Asymptotic normality of minimum L1-norm estimation in linear modules.Chinese Science Ser A,1990,33(5):449～463
[6] Wang J.Asymptotic normality of L1-estimators in nonlinear regression.J Multivariate Anal,1995,54(2):227～238
[7] Cipra T,Romera M.Recursive time series methods in L1-norm,L1-statistical analysis and related method.Amsterdam:North-Holland,1992.233～243
[8] Bloomfield P,Steiger W.Least absolute deviations:theory,applications and algorithms.Boston:Birkhause,1983.56～79
[9] Gross H,Steiger W.Least absolute deviation estimates in autoregression with infinite variance.J Appl Prob,1979,16(1):104～116
[10] 王立洪,王金德.时间序列模型L1-估计量的极限分布:平稳自回归模型.数学学报,1999,42(5):905～912
[11] Bell C B,Smith E P.Inference for non-negative autoregressive schemes.Communications in Statistics-Theory Methods,1986,15(8):2267～2293
[12] Andel J.Non-negative autoregressive processes.J Times Ser Anal,1989,10:1～11
[13] Andel J,Grarrido M.Bayesian analysis of non-negative AR (2) processes.Statistics,1991,22(4):579～588
[14] Nagaraj N K,Fuller W A.Estimation of the parameters of linear time series models subject to nonlinear restrictions.Ann statistics,1991,19:1143～1154
[15] Box G P,Jenkins G M.时间序列分析:预测与控制.顾岚译.北京:中国统计出版社,1997.23～98
[16] Brockwell P,Davis R.Time series:theory and methods.Berlin:Soringer-Verlag,1987.204～209
[17] Wang J.Asymptotics of least-squares estimators for constrained nonlinear regression.Ann Statistics,1996,24:1316～1326

## 相似文献/References:

[1]贺传富,周惠新,虞献群.非线性约束条件的污染数据的L2-估计[J].东南大学学报(自然科学版),2004,34(5):686.[doi:10.3969/j.issn.1001-0505.2004.05.028]
He Chuanfu,Zhou Huixin,Yu Xianqun.L 2-estimators of contaminated data with nonlinear constraints[J].Journal of Southeast University (Natural Science Edition),2004,34(5):686.[doi:10.3969/j.issn.1001-0505.2004.05.028]