Premium
Structural Time Series Models with Feedback Mechanisms
Author(s) -
Guo Wensheng,
Brown Morton B.
Publication year - 2000
Publication title -
biometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.298
H-Index - 130
eISSN - 1541-0420
pISSN - 0006-341X
DOI - 10.1111/j.0006-341x.2000.00686.x
Subject(s) - series (stratigraphy) , computer science , class (philosophy) , state space , artificial intelligence , mathematics , statistics , paleontology , biology
Summary. Structural time series models have applications in many different fields such as biology, economics, and meteorology. A structural time series model can be represented as a state‐space model where the states of the system represent the unobserved components and the structural parameters have clear interpretations. This paper introduces a class of structural time series models that incorporate feedback from the latent components of the history. An iterative procedure is proposed for estimation. These models allow flexible and robust feedback mechanisms, have clear interpretations, and have a computationally efficient estimation procedure. They are applied to hormone data to characterize hormone secretion and to explore a potential feedback mechanism.