Least Absolute Deviation Estimation for Regression with ARMA Errors

被引：0

作者：

Richard A. Davis

William T. M. Dunsmuir

机构：

[1] Colorado State University,

[2] University of New South Wales,undefined

来源：

Journal of Theoretical Probability | 1997年 / 10卷

关键词：

ARMA process; regression; least absolute deviation estimation; central limit theorem;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

The asymptotic normality for least absolute deviation estimates of the parameters in a linear regression model with autoregressive moving average errors is established under very general conditions. The method of proof is based on a functional limit theorem for the LAD objective function.

引用

页码：481 / 497

页数：16

共 9 条

[1] Davis R. A.(1996)Gauss-Newton and Stoch. Proc. Appl. 63 75-95
[2] Davis R. A.(1996)-Estimation for ARMA processes with infinite variance Econometric Theory 12 1-29
[3] Dunsmuir W. T. M.(1992)Maximum likelihood estimation for MA(1) processes with a root on or near the unit circle Stoch. Proc. Appl. 40 145-180
[4] Davis R. A.(1991)-estimation for autoregressions with infinite variance J. Time Series Anal. 12 95-104
[5] Knight K.(1991)Strong consistency and asymptotic normality of Econometric Theory 7 186-199
[6] Liu J.(undefined) estimates of the autoregressive moving-average model undefined undefined undefined-undefined
[7] Dunsmuir W. T. M.(undefined)Asymptotic for least absolute deviation regression estimators undefined undefined undefined-undefined
[8] Spencer N. M.(undefined)undefined undefined undefined undefined-undefined
[9] Pollard D.(undefined)undefined undefined undefined undefined-undefined

← 1 →