Summary
We show how a number of commonly used estimates of the inverse autocorrelation function can be modified to deal with outlier contaminated data. The robust analogues of the orthogonal and interpolation based techniques appear to be new, and provide an alternative to the robust autoregressive approach. We examine the performance of these techniques in a large scale numerical experiment. This shows significant improvements in performance in outlier contaminated data when robust techniques are used. While there was no uniformly best robust technique, our experiments support the use of the autoregressive approach to avoid catastrophic reductions in performance, and robust interpolation for short series corrupted by few outliers.
Similar content being viewed by others
References
Allende, H. and Heiler, S. (1992). Recursive generalized M estimates for autoregressive moving average models. J. Time Ser. Anal., 13, 1–18.
Baragona, R. and Battaglia, F. (1984). Estimating inverse correlations: a simulation study. Dipartimento di Statistica, Probabilitπ e Statistiche Applicate, Università ‘La Sapienza’ di Rome, serie A, 10.
Battaglia, F. (1986). Recursive estimation of the inverse correlation function. Statistica, 46, 75–82.
Battaglia, F. (1988). On the estimation of the inverse correlation function. J. Time Ser. Anal., 9, 1–10.
Battaglia, F. (1993). Selection of a linear interpolator for time series. Statistica Sinica, 3, 255–259.
Battaglia, F. and Baragona, R. (1992). Linear interpolators and the outliers problem in time series. Metron, 50, 79–97.
Battaglia, F. and Bhansali, R. J. (1987). Estimation of the interpolation error variance and an index of linear determinism. Biometrika, 74, 771–779.
Bender, R. and Grouven, U. (1993). On the choice of the number of residual autocovariances for the portmanteau test of multivariate autoregressive models. Commun. Statist.-Simul. Comput., 22, 19–32.
Bhansali, R. J. (1980). Autoregressive and window estimates of the inverse correlation function. Biometrika, 67, 551–566.
Bhansali, R. J. (1983a). A simulation study of autoregressive and window estimators of the inverse correlation function. J. Roy. Statist. Soc., C 32, 141–149.
Bhansali, R. J. (1983b). Estimation of the order of a moving average model from autoregressive and window estimates of the inverse correlation function. J. Time Ser. Anal., 4, 137–162.
Bhansali, R. J. (1984). Asymptotic distribution of the autoregressive estimates of the inverse correlation function. Statistica, 44, 107–116.
Bhansali, R. J. (1990). On a relationship between the inverse of a stationary covariance matrix and the linear interpolator. J. Appl. Probab., 27, 156–170.
Chen, M. (1992). On the asymptotic properties of the autoregressive estimates of the inverse autocorrelation function I: strong convergence and rate. Appl. Math. J. Chin. Univ., 7, 216–227.
Chen, M. (1993). On the asymptotic properties of the autoregressive estimates of the inverse autocorrelation function II: asymptotic normality. Appl. Math. J. Chin. Univ., 8, 1–16.
Cleveland, W. S. (1972). The inverse autocorrelations of a time series and their applications. Technometrics, 14, 277–298.
Dempster, A. P. (1972). Covariance selection. Biometrics, 28, 157–176.
Efron, A. J. and Jeen, H. (1994). Detection in impulsive noise based on robust whitening. IEEE Trans. Signal. Proc., 42, 1572–1576.
Glendinning, R. H. (1998). Determining the order of an ARMA model from outlier contaminated data. Commun. Statist. Theory Meth., 27, 13–40.
Glendinning, R. H. (1999). A robust Yu-Lin strategy. Bulletin of the International Statistical Institute, 52nd Session, August 10–18, 1999, Helsinki, Finland, Tome LVIII, Book 1, 393–394. Finland, 1999.
Hosking, J. R. M. (1980). The asymptotic distribution of the sample inverse autocorrelations of an autoregressive moving average process. Biometrika, 67, 223–226.
Kanto, A. (1987). A formula for the inverse autocorrelation function of an autoregressive process. J. Time. Ser. Anal., 8, 311–312.
Konishi, S. and Kitagawa, G. (1996). Generalized information criteria in model selection. Biometrika, 83, 875–890.
Ledolter, J. (1989). The effect of additive outliers on the forecasts from ARIMA models. Int. J. Forecast., 5, 231–240.
Mardia, K. V. (1970). Measures of multivariate skewness and kurtosis with applications. Biometrika, 57, 519–530.
Martin, R. D. (1979). Approximate conditional mean type smoothers and interpolators. In: T. Gasser and M. Rosenblatt (Eds.), Smoothing Techniques for Curve Estimation (pp. 117–143). Springer, Berlin.
Martin, R. D. (1980). Robust estimation of autoregressive models, In Directions in Time Series, Ed. D. R. Brillinger and G. C. Tiao, Haywood California: Institute of Mathematical Statistics Publications, pp. 228–262
Martin, R. D. and Thomson, D. J. (1982). Robust resistant spectrum estimation. Proc. IEEE, 70, 1097–1115.
Martin, R. D. and Yohai, V. J. (1985). Robustness in time series and estimating ARMA models. In: E. J. Hannan, P. R. Krishnaiah and M. M. Rao, (Eds.), Handbook of Statistics5 (pp. 119–155). North-Holland, Amsterdam.
Masarotto, G. (1987). Robust identification of autoregressive-moving average models. J. Roy. Statist. Soc., C 36, 214–220.
McClave, J. T. (1974). A comparison of moving average estimation procedures. Commun. Statist., 3, 865–883.
Peña, D. and Maravall, A. (1991). Interpolation, outliers and inverse autocorrelations. Commun. Statist.-Theory Meth., 20, 3175–3186.
Ronchetti, E. (1997). Robustness aspects of model choice. Statistica Sinica, 7, 327–338.
Schmid, W. (1996). An outlier test for time series based on a two-sided predictor. J. Time Ser. Anal., 17, 497–510.
Shumway, R. H. (1982). Discriminant analysis for time series. In: P. R. Krishnaiah and L. N. Kanal (Eds.), Handbook of Statistics2 (pp. 1–46). North-Holland, Amsterdam.
Subba Rao, T. and Gabr, M. M. (1989). The estimation of spectrum, inverse spectrum and inverse autocovariances of a stationary time series. J. Time Ser. Anal., 10, 183–202.
Tatum, L. G. and Hurvich, C. M. (1993). High breakdown methods of time series analysis. J. Roy. Statist. Soc., 55, 881–896.
Yu, G-H. and Lin, Y-C. (1991). A methodology for selecting subset autoregressive time series models. J. Time Ser. Anal., 12, 363–373.
Yuan, J. and Subba Rao, T. (1993a). Spectral estimation for random fields with applications to Markov modeling and texture classification. In: R. Chellappa and A.K. Jain (Eds.), Markov Random Fields, Theory and Applications (pp. 179–209). Academic Press, Boston.
Yuan, J. and Subba Rao, T. (1993b). Characterization and estimation for multivariate Markov random fields by spectral methods. In: C. R. Rao (Ed.), Multivariate Analysis: Future Directions (pp. 467–478). Elsevier Science Publishers, Amsterdam.
Wichmann, B. A. and Hill, I. D. (1982). Algorithm AS 183. An efficient and portable pseudo-random number generator. J. Roy. Statist. Soc., C 31, 188–190.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Glendinning, R.H. Estimating the Inverse Autocorrelation Function from Outlier Contaminated Data. Computational Statistics 15, 541–565 (2000). https://doi.org/10.1007/s001800000048
Published:
Issue Date:
DOI: https://doi.org/10.1007/s001800000048