Oracally efficient estimation of autoregressive error distribution with simultaneous confidence band
Authors:
- Jiangyan WangJWJiangyan Wang
- Rong LiuRLRong Liu
- Fuxia ChengFCFuxia Cheng
- Lijian YangLijian Yang
Open Access
- 1 April 2014
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 42 (2) , 654-668
Abstract
We propose kernel estimator for the distribution function of unobserved errors in autoregressive time series, based on residuals computed by estimating the autoregressive coefficients with the Yule–Walker method. Under mild assumptions, we establish oracle efficiency of the proposed estimator, that is, it is asymptotically as efficient as the kernel estimator of the distribution function based on the unobserved error sequence itself. Applying the result of Wang, Cheng and Yang [J. Nonparametr. Stat. 25 (2013) 395–407], the proposed estimator is also asymptotically indistinguishable from the empirical distribution function based on the unobserved errors. A smooth simultaneous confidence band (SCB) is then constructed based on the proposed smooth distribution estimator and Kolmogorov distribution. Simulation examples support the asymptotic theory.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Change‐Point Tests for the Error Distribution in Non‐parametric RegressionScandinavian Journal of Statistics, 2009
- Kernel estimation of multivariate cumulative distribution functionJournal of Nonparametric Statistics, 2008
- A New Test for the Parametric Form of the Variance Function in Non-Parametric RegressionJournal of the Royal Statistical Society Series B: Statistical Methodology, 2007
- BOOTSTRAP TESTS FOR THE ERROR DISTRIBUTION IN LINEAR AND NONPARAMETRIC REGRESSION MODELSAustralian & New Zealand Journal of Statistics, 2006
- A note on the Bickel–Rosenblatt test in autoregressive time seriesStatistics & Probability Letters, 2005
- Estimating functionals of the error distribution in parametric and nonparametric regressionJournal of Nonparametric Statistics, 2004
- A consistent test for conditional symmetry in time series modelsJournal of Econometrics, 2001
- Testing for Parameter Constancy in Linear Regressions: An Empirical Distribution Function ApproachEconometrica, 1996
- Extreme Value Theory for Moving Average ProcessesThe Annals of Probability, 1986
- On Some Global Measures of the Deviations of Density Function EstimatesThe Annals of Statistics, 1973