Premium
Reasoning about non‐linear AR models using expectation maximization
Author(s) -
Arnold M.
Publication year - 2003
Publication title -
journal of forecasting
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.543
H-Index - 59
eISSN - 1099-131X
pISSN - 0277-6693
DOI - 10.1002/for.866
Subject(s) - autoregressive model , maximization , expectation–maximization algorithm , mathematics , state (computer science) , linear regression , computer science , linear model , process (computing) , identification (biology) , mathematical optimization , algorithm , econometrics , maximum likelihood , statistics , machine learning , botany , biology , operating system
A simplified version of the expectation maximization (EM) algorithm is applied to search for optimal state sequences in state‐dependent AR models whereby no prior knowledge about the state equation is necessary. These sequences can be used to draw conclusions about functional dependencies between the observed process and estimated AR coefficients. Consequently this approach is especially helpful in the identification of functional–coefficient AR models where the coefficients are controlled by the process itself. The approximation of regression functions in first‐order non‐linear AR models and the localization of multiple thresholds in self‐exciting threshold autoregressive models are demonstrated as examples. Copyright © 2003 John Wiley & Sons, Ltd.