| Title | Markov-switching model selection using Kullback-Leibler divergence |
| Authors | Smith, Aaron Naik, Prasad A. Tsai, Chih-Ling |
| Affiliation | Univ Calif Davis, Dept Agr & Resource Econ, Davis, CA 95616 USA. Univ Calif Davis, Grad Sch Management, Davis, CA 95616 USA. Peking Univ, Guanghua Sch Management, Beijing, Peoples R China. Univ Calif Davis, Dept Agr & Resource Econ, 1 Shields Ave, Davis, CA 95616 USA. |
| Keywords | advertising effectiveness business cycles EM algorithm hidden Markov models information criterion Markov-switching regression MAXIMUM-LIKELIHOOD ESTIMATOR TIME-SERIES PROBABILISTIC FUNCTIONS AUTOREGRESSIVE MODELS INFORMATION CRITERIA BUSINESS-CYCLE LINEAR-MODELS REGIME SHIFTS BAYES FACTORS RATIO TEST |
| Issue Date | 2006 |
| Publisher | journal of econometrics |
| Citation | JOURNAL OF ECONOMETRICS.2006,134,(2),553-577. |
| Abstract | In Markov-switching regression models, we use Kullback-Leibler (KL) divergence between the true and candidate models to select the number of states and variables simultaneously. Specifically, we derive a new information criterion, Markov switching criterion (MSC), which is an estimate of KL divergence. MSC imposes an appropriate penalty to mitigate the over-retention of states in the Markov chain, and it performs well in Monte Carlo studies with single and multiple states, small and large samples, and low and high noise. We illustrate the usefulness of MSC via applications to the U.S. business cycle and to media advertising. (c) 2005 Elsevier B.V. All rights reserved. |
| URI | http://hdl.handle.net/20.500.11897/251530 |
| ISSN | 0304-4076 |
| DOI | 10.1016/j.jeconom.2005.07.005 |
| Indexed | SCI(E) EI SSCI |
| Appears in Collections: | 光华管理学院 |
