A new algorithm for the ARMA model order via pivot-neighbors comparisons

This paper presents a new algorithm for the determination of the ARMA model orders based on a rounding approach which is implemented to deal with the precision of binary words. The rounding approach uses the floor and the ceiling functions. The proposed algorithm is based on selecting a sequence of pivot cells values from the well known minimum eigenvalue (MEV) method developed by Liang et. al. [6]. It uses the floor and the ceiling functions of the pivot cells values and the values of its neighbors to search for the corner that contains the estimates of the true orders. The observed sequence may be contaminated by additive Gaussian noise. Simulation examples are given to illustrate the effectiveness of the proposed technique for different signal to noise ratios.