Mario Blaum, John L. Fan, et al.
IEEE International Symposium on Information Theory - Proceedings
A change-point model is considered where the canonical parameter of an exponential family drifts from its control value at an unknown time and changes according to a broken-line regression. Necessary and sufficient conditions are obtained for the existence of consistent change-point estimators. When sufficient conditions are met, it is shown that the maximum likelihood estimator of the change point is consistent, unlike the classical abrupt change-point models. Results are extended to the case of nonlinear trends and nonequidistant observations. © 2003 Elsevier B.V. All rights reserved.
Mario Blaum, John L. Fan, et al.
IEEE International Symposium on Information Theory - Proceedings
Kafai Lai, Alan E. Rosenbluth, et al.
SPIE Advanced Lithography 2007
Paul J. Steinhardt, P. Chaudhari
Journal of Computational Physics
L Auslander, E Feig, et al.
Advances in Applied Mathematics