Spectral estimation: An overdetermined rational model equation approach

In seeking rational models of time series, the concept of approximating second-order statistical relationships (i.e., the Yule-Walker equations) is often explicitly or implicitly invoked. The parameters of the hypothesized rational model are typically selected so that these relationships "best represent" a set of autocorrelation lag estimates computed from time series observations. One of the objectives of this paper will be that of establishing this fundamental approach to the generation of rational models. An examination of many popular contemporary spectral estimation methods reveals that the parameters of a hypothesized rational model are estimated upon using a "minimal" set of Yule-Walker equation evaluations. This results in an undesired parameter hypersensitivity and a subsequent decrease in estimation performance. To counteract this parameter hypersensitivity, the concept of using more than the minimal number of Yule-Walker equation evaluations is herein advocated. It is shown that by taking this overdetermined parametric evaluation approach, a reduction in data-induced model parameter hypersensitivity is obtained, and a corresponding improvement in modeling performance results. Moreover, upon adapting a singular value decomposition representation of an extended-order autocorrelation matrix estimate to this procedure, a desired model order determination method is obtained and a further significant improvement in modeling performance is achieved. This approach makes possible the generation of low-order high-quality rational spectral estimates from short data lengths.

[1]  Arthur Schuster,et al.  On the investigation of hidden periodicities with application to a supposed 26 day period of meteorological phenomena , 1898 .

[2]  G. Yule.  On a Method of Investigating Periodicities in Disturbed Series, with Special Reference to Wolfer's Sunspot Numbers , 1927 .

[3]  Gilbert T. Walker,et al.  On Periodicity in Series of Related Terms , 1931 .

[4]  N. Levinson.  The Wiener (Root Mean Square) Error Criterion in Filter Design and Prediction , 1946 .

[5]  James Durbin,et al.  The fitting of time series models , 1960 .

[6]  J. P. Burg,et al.  Maximum entropy spectral analysis. , 1967 .

[7]  J. Shanks.  RECURSION FILTERS FOR DIGITAL PROCESSING , 1967 .

[8]  P. Welch.  The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms , 1967 .

[9]  H. Akaike.  Fitting autoregressive models for prediction , 1969 .

[10]  H. Akaike.  Power spectrum estimation through autoregressive model fitting , 1969 .

[11]  H. Akaike.  Fitting autoregressive models for prediction , 1969 .

[12]  Will Gersch,et al.  Estimation of the autoregressive parameters of a mixed autoregressive moving-average time series , 1970 .

[13]  R. Mehra.  On-line identification of linear dynamic systems with applications to Kalman filtering , 1971 .

[14]  H. Akaike.  Maximum likelihood identification of Gaussian autoregressive moving average models , 1973 .

[15]  V. Pisarenko.  The Retrieval of Harmonics from a Covariance Function , 1973 .

[16]  P. Newbold.  The exact likelihood function for a mixed autoregressive-moving average process , 1974 .

[17]  N. Andersen.  On the calculation of filter coefficients for maximum entropy spectral analysis , 1974 .

[18]  H. Akaike.  A new look at the statistical model identification , 1974 .

[19]  R. Mehra,et al.  Computational aspects of maximum likelihood estimation and reduction in sensitivity function calculations , 1974 .

[20]  E. Parzen.  Some recent advances in time series modeling , 1974 .

[21]  Daniel Graupe,et al.  Identification of autoregressive moving-average parameters of time series , 1975 .

[22]  B. Widrow,et al.  Adaptive noise cancelling: Principles and applications , 1975 .

[23]  M. Morf,et al.  Fast algorithms for recursive identification , 1976, 1976 IEEE Conference on Decision and Control including the 15th Symposium on Adaptive Processes.

[24]  T. Ulrych,et al.  Time series modeling and maximum entropy , 1976 .

[25]  J. Makhoul.  Stable and efficient lattice methods for linear prediction , 1977 .

[26]  B. Dickinson,et al.  Efficient solution of covariance equations for linear prediction , 1977 .

[27]  Sven Treitel,et al.  Spectral Estimation: Fact or Fiction , 1978, IEEE Transactions on Geoscience Electronics.

[28]  C. Ansley.  An algorithm for the exact likelihood of a mixed autoregressive-moving average process , 1979 .

[29]  L. Scharf,et al.  A note on covariance-invariant digital filter design and autoregressive moving average spectrum analysis , 1979 .

[30]  M. Kaveh.  High resolution spectral estimation for noisy signals , 1979 .

[31]  L. Ljung,et al.  New inversion formulas for matrices classified in terms of their distance from Toeplitz matrices , 1979 .

[32]  I. Konvalinka,et al.  Simultaneous estimation of poles and zeros in speech analysis and ITIF-iterative inverse filtering algorithm , 1979 .

[33]  Mostafa Kaveh,et al.  On some suboptimum ARMA spectral estimators , 1980 .

[34]  A. Laub,et al.  The singular value decomposition: Its computation and some applications , 1980 .

[35]  Steven Kay,et al.  A new ARMA spectral estimator , 1980 .

[36]  J. Cadzow,et al.  High performance spectral estimation--A new ARMA method , 1980 .

[37]  R. Kashyap.  Inconsistency of the AIC rule for estimating the order of autoregressive models , 1980 .

[38]  A. A. Beex,et al.  Covariance sequence approximation for parametric spectrum modeling , 1981 .

[39]  James A. Cadzow.  Autoregressive Moving Average Spectral Estimation: A Model Equation Error Procedure , 1981, IEEE Transactions on Geoscience and Remote Sensing.

[40]  T. Henderson,et al.  Geometric methods for determining system poles from transient response , 1981 .

[41]  Ramdas Kumaresan,et al.  Singular value decomposition and spectral analysis , 1981, 1981 20th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes.

[42]  S.M. Kay,et al.  Spectrum analysis—A modern perspective , 1981, Proceedings of the IEEE.

[43]  J. Cadzow,et al.  Two-dimensional spectral estimation , 1981 .

[44]  James A Cadzow.  ARMA Spectral Estimation: An Efficient Closed Form Procedure. , 1981 .

[45]  James A. Cadzow,et al.  Data adaptive ARMA modeling of time series , 1982, ICASSP.

[46]  Joël Le Roux,et al.  Comparison of some algorithms for identifying autoregressive signals in the presence of observation noise , 1982, ICASSP.

[47]  James A. Cadzow.  ARMA Modeling of Time Series , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[48]  J. L. Hock,et al.  An exact recursion for the composite nearest‐neighbor degeneracy for a 2×N lattice space , 1984 .