Abstract

The paper discusses the application of multiivariabIe AR, ARMA modelling and the associated structure and parameter estimation methods in spectral analysis of nuclear noise processes. The methods selected for identification are off-line least-squares (LS) and Leoinson-type “recursive in structure” procedures extended by the use of information criteria RIC, BIC, Based on an identified four variable RRMA model, a simulational study is presented to investigate the effect of choosing a particular LS method and the effect of changes in structure estimation on the shape of spectral estimates

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call