Estimating the order of sinusoidal models using the adaptively penalized likelihood approach: Large sample consistency properties

Recently, the paper 2 introduced a method for model order estimation based on penalizing adaptively the likelihood (PAL). In this paper, we use the PAL based order estimation method for a nonlinear sinusoidal model and study its asymptotic statistical properties. We prove that the estimator of the model order using the PAL rule is consistent. Simulation examples are presented to illustrate the performance of the PAL method for small sample sizes and to compare it with that of three information criterion-based methods. In this paper, we use the PAL based order estimation method for estimating the number of components of a superimposed nonlinear sinusoidal model.We have proved that the estimator of the model order using the PAL rule is large sample consistent.Simulation examples are presented to illustrate the performance of the PAL method for small sample sizes and to compare it with three standard methods, namely, the usual AIC, the usual BIC and the asymptotic MAP rule.The PAL rule can also be extended for estimating the number of components for similar nested superimposed nonlinear 1-d and 2-d signal models.

[1]  E. Lehmann.  Testing Statistical Hypotheses , 1960 .

[2]  S. S. Wilks.  Sample Criteria for Testing Equality of Means, Equality of Variances, and Equality of Covariances in a Normal Multivariate Distribution , 1946 .

[3]  Petar M. Djuric,et al.  Asymptotic MAP criteria for model selection , 1998, IEEE Trans. Signal Process..

[4]  Tiee-Jian Wu,et al.  A comparative study of model selection criteria for the number of signals , 2008 .

[5]  Steven Kay,et al.  Inconsistency of the MDL: On the Performance of Model Order Selection Criteria With Increasing Signal-to-Noise Ratio , 2011, IEEE Transactions on Signal Processing.

[6]  Petre Stoica,et al.  Model order estimation via penalizing adaptively the likelihood (PAL) , 2013, Signal Process..

[7]  C. Raghavendra Rao,et al.  On model selection , 2001 .

[8]  Debasis Kundu,et al.  Detecting the number of signals for an undamped exponential model using cross-validation approach , 2000, Signal Process..

[9]  J. M. Francos,et al.  Strong consistency of a family of model order selection rules for estimating 2D sinusoids in noise , 2008 .

[10]  Debasis Kundu,et al.  On asymptotic behavior of least squares estimators and the confidence intervals of the superimposed exponential signals , 1999, Signal Process..

[11]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

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

[13]  Pinyuen Chen.  A selection procedure for estimating the number of signal components , 2002 .

[14]  Y. Selen,et al.  Model-order selection: a review of information criterion rules , 2004, IEEE Signal Processing Magazine.

[15]  Kai Lai Chung,et al.  A Course in Probability Theory , 1949 .

[16]  Debasis Kundu,et al.  Sequential estimation of the sum of sinusoidal model parameters , 2008 .

[17]  Thomas Kailath,et al.  Detection of signals by information theoretic criteria , 1985, IEEE Trans. Acoust. Speech Signal Process..

[18]  Petre Stoica,et al.  On the Proper Forms of BIC for Model Order Selection , 2012, IEEE Transactions on Signal Processing.

[19]  Debasis Kundu,et al.  Asymptotic properties of the least squares estimates of 2-D exponential signals , 1996, Multidimens. Syst. Signal Process..

[20]  Joseph M. Francos,et al.  Strong consistency of the over- and underdetermined LSE of 2-D exponentials in white noise , 2005, IEEE Transactions on Information Theory.

[21]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[22]  B. G. Quinn,et al.  ESTIMATING THE NUMBER OF TERMS IN A SINUSOIDAL REGRESSION , 1989 .

[23]  Joseph M. Francos,et al.  MAP model order selection rule for 2-D sinusoids in white noise , 2005, IEEE Transactions on Signal Processing.