A CONSTRAINED LEAST SQUARES FITTING TECHNIQUE FOR ARMA MODELING

摘要

Several ARMA modeling approaches are addressed.In these methods only part of a correlationsequence is employed for estimating parameters.It is satisfying,if the given correlation sequence is ofreal ARMA,since an ARMA process can be completely determined by part of its correlation se-quence.But for the case of a measured correlation sequence the whole sequence may be used to re-duce the effect of error on model parameter estimation.In addition,these methods now do not guar-antee a nonnegative spectral estimate.In view of the above-mentioned fact,a constrained leastsquares fitting technique is proposed which utilizes the whole measured correlation sequence and guar-antees a nonnegative spectral estimate.