Diagnostics for testing model goodness-of-fit and badness-of-fit for time series data are formulated by considering a convenient metrization of a spectral density's departure from constancy. The method is illustrated through numerical experiments and several case studies.
ARMA, EXP Models, Frequency Domain, Nonstationary Time Series
[PDF] or
denotes a file in Adobe’s Portable Document Format.
To view the file, you will need the
Adobe® Acrobat® Reader
available free from Adobe.