Robust estimation of SARIMA models: Application to short-term load forecasting

  title={Robust estimation of SARIMA models: Application to short-term load forecasting},
  author={Yacine Chakhchoukh and Patrick Panciatici and Pascal Bondon},
  journal={2009 IEEE/SP 15th Workshop on Statistical Signal Processing},
This paper presents a new robust method to estimate the parameters of a SARIMA model. This method uses robust autocorrelations estimates based on sample medians coupled with a robust filter cleaner which rejects deviant observations. Our procedure is compared with other robust methods via evaluation of the different robustness measures such as maximum bias, breakdown point and influence function. The asymptotic properties of our method (strong consistency and central limit theorem) are… CONTINUE READING


Publications referenced by this paper.
Showing 1-4 of 4 references

Influence functionals for time series

R. Douglas Martin, Vı́ctor J. Yohai
Ann. Statist., vol. 14, no. 3, pp. 781–855, 1986, With discussion. • 1986
View 2 Excerpts

Maximum likelihood fitting of ARMA models to time series with missing observations

Richard H. Jones
Technometrics, vol. 22, no. 3, pp. 389–395, 1980. • 1980
View 1 Excerpt

On the Bahadur representation of sample quantiles for mixing processes

Ryôzô Yokoyama
Tsukuba J. Math., vol. 2, pp. 75–90, 1978. 80 2009 IEEE/SP 15th Workshop on Statistical Signal Processing • 1978
View 1 Excerpt

Robust Bayesian estimation for the linear model and robustifying the Kalman filter

C. Johan Masreliez, R. Douglas Martin
IEEE Trans. Automatic Control, vol. AC-22, no. 3, pp. 361–371, 1977. • 1977
View 2 Excerpts

Similar Papers

Loading similar papers…