Akaike's final prediction error criterion revisited | IEEE Conference Publication | IEEE Xplore

Akaike's final prediction error criterion revisited


Abstract:

When local identification of a nonstationary ARX system is carried out, two important decisions must be taken. First, one should decide upon the number of estimated param...Show More

Abstract:

When local identification of a nonstationary ARX system is carried out, two important decisions must be taken. First, one should decide upon the number of estimated parameters, i.e., on the model order. Second, one should choose the appropriate estimation bandwidth, related to the (effective) number of input-output data samples that will be used for identification/tracking purposes. Failure to make the right decisions results in the model deterioration, both in the quantitative and qualitative sense. In this paper, we show that both problems can be solved using the suitably modified Akaike's final prediction error criterion. The proposed solution is next compared with another one, based on the Rissanen's predictive least squares principle.
Date of Conference: 05-07 July 2017
Date Added to IEEE Xplore: 23 October 2017
ISBN Information:
Conference Location: Barcelona, Spain

References

References is not available for this document.