Key points are not available for this paper at this time.
SUMMARY The paper shows how possible change in a system generating a time series may be studied by comparing forecasts made from a model built on data prior to the suspected change with data actually occurring. An environmental example illustrates the decomposition of the overall criterion into relevant components and shows how difficulties can occur in distinguishing alternative models for change. The relation to surveillance problems and to intervention analysis is briefly discussed.
Box et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: