Abstract: Several ARMA modeling approaches are addressed. In these methods only part of the correlation sequence is employed for estimating parameters. It is satisfying if the given correlation sequence is of real ARMA, since an ARMA process can be completely determined by part of its correlation sequence. But for case of measured correlation sequence the whole sequence may be used to reduce the effect of error on model parameter estimation. In addition, these methods now do not guarantee a nonnegative spectral estimate. In view of the above mentioned fact, a constrained least squares fitting technique is proposed which utilizes the wlole measured correlation sequence and guarantees a nonnegative estimate.