THEORY AND APPLICATION OF AN INFERENCE MODEL FOR NON-STATIONARY TIME SERIES MEANS.
CARNEGIE INST OF TECH PITTSBURGH PA GRADUATE SCHOOL OF INDUSTRIAL ADMINISTRATION
Pagination or Media Count:
Complex time series models, such as consumer brand shifting analyses, have required assumptions of parameter stability because statistical models to deal with parameter change were not available. A model is developed here to make inferences about a possibly nonstationary time series mean generating data with Gaussian error. Estimators which are efficient in a special sense are presented, along with examples and suggested applications of the method to brand switching problems. Author