The Annals of Statistics

On residual empirical processes of stochastic regression models with applications to time series

Sangyeol Lee and Ching-Zong Wei

Full-text: Open access

Abstract

Motivated by Gaussian tests for a time series, we are led to investigate the asymptotic behavior of the residual empirical processes of stochastic regression models. These models cover the fixed design regression models as well as general AR$(q)$ models. Since the number of the regression coeffi-cients is allowed to grow as the sample size increases, the obtained results are also applicable to nonlinear regression and stationary AR$(\infty)$ models. In this paper, we first derive an oscillation-like result for the residual em-pirical process. Then, we apply this result to autoregressive time series. In particular, for a stationary AR$(\infty)$ process, we are able to determine the order of the number of coefficients of a fitted AR$(q_n)$ model and obtain the limiting Gaussian processes. For an unstable AR$(q)$ process, we show that if the characteristic polynomial has a unit root 1, then the limiting process is no longer Gaussian. For the explosive case, one of our side results also provides a short proof for the Brownian bridge results given by Koul and Levental.

Article information

Source
Ann. Statist., Volume 27, Number 1 (1999), 237-261.

Dates
First available in Project Euclid: 5 April 2002

Permanent link to this document
https://projecteuclid.org/euclid.aos/1018031109

Digital Object Identifier
doi:10.1214/aos/1018031109

Mathematical Reviews number (MathSciNet)
MR1701109

Zentralblatt MATH identifier
0943.62092

Subjects
Primary: 60F17: Functional limit theorems; invariance principles
Secondary: 62M10: Time series, auto-correlation, regression, etc. [See also 91B84]

Keywords
Gaussian tests residual empirical process stochastic regression model stationary $AR(\infty)$ process oscillation-like result unstable AR(q) process explosive process Brownian bridge

Citation

Lee, Sangyeol; Wei, Ching-Zong. On residual empirical processes of stochastic regression models with applications to time series. Ann. Statist. 27 (1999), no. 1, 237--261. doi:10.1214/aos/1018031109. https://projecteuclid.org/euclid.aos/1018031109


Export citation

References

  • Berk, K. N. (1974). Consistent autoregressive spectral estimates. Ann. Statist. 2 489-502.
  • Boldin, M. V. (1982). Estimation of the distribution of noise in an autoregressive scheme. Theory Probab. Appl. 27 886-871.
  • Brockwell P. J. and Davis, R. A. (1990). Time Series: Theory and Methods, 2nd ed. Springer, New York.
  • Chan, N. H. and Wei, C. Z. (1988). Limiting distribution of least squares estimates of unstable autoregressive processes. Ann. Statist. 16 367-401.
  • Cram´er, H. (1974). Mathematical Methods of Statistics. Princeton Univ. Press.
  • Durbin, J. (1973). Weak convergence of the sample distribution function when parameters are estimated. Ann. Statist. 1 279-290.
  • Epps, T. W. (1987). Testing that a stationary time series is Gaussian. Ann. Statist. 15 1683-1698.
  • Grenander, U. and Szeg ¨o, G. (1958). Toplitz Forms and Their Applications. Univ. California Press, Berkeley.
  • Hinich, M. J. (1982). Testing for Gaussianality and linearity of a stationary time series. J. Time Series Anal. 3 169-176.
  • Koul, H. L. (1992). Weighted Empiricals and Linear Models. IMS, Hayward, CA.
  • Koul, H. L. and Levental, S. (1989). Weak convergence of residual empirical process in explosive autoregression. Ann. Statist. 17 1784-1794.
  • Kreiss, J. P. (1988). Asymptotic for the empirical distribution of residuals in autoregression with infinite order. Unpublished manuscript.
  • Lee, S. (1991). Testing whether a time series is Gaussian. Ph.D. dissertation, Dept. Mathematics, Univ. Maryland.
  • Lii, K. S. and Rosenblatt, M. (1982). Deconvolution and estimation of transfer function phase and coefficients for nongaussian linear processes. Ann. Statist. 10 1195-1208.
  • Pierce, D. A. (1985). Testing normality in autoregressive models. Biometrika 72 293-297.
  • Rosenblatt, M. (1985). Stationary Sequences and Random Fields. Birkh¨auser. Boston.
  • Roussas, G. (1972). Contiguity of Probability Measures: Some Applications in Statistics. Cambridge Univ. Press.
  • Shibata, R. (1980). Asymptotically efficient selection of the model for estimating parameters of a linear process. Ann. Statist. 8 147-164.
  • Shorack, G. and Wellner, J. (1986). Empirical Processes with Applications to Statistics. Wiley, New York.
  • Stute, W. (1982). The oscillation behavior of empirical processes. Ann. Probab. 10 86-107.
  • Subba Rao, T. and Gabr, M. M. (1980). A test for linearity of stationay time series. J. Time Series Anal. 1 145-158.
  • Wei, C. Z. (1992). On predictive least squares principles. Ann. Statist. 20 1-42.