2015 Fiscal Year Final Research Report
A Bayesian Markov switching almost ideal demand systems model, model selection, and its applications
Project/Area Number |
25590051
|
Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
Allocation Type | Multi-year Fund |
Research Field |
Economic statistics
|
Research Institution | University of Tsukuba |
Principal Investigator |
|
Project Period (FY) |
2013-04-01 – 2016-03-31
|
Keywords | Bayesian estimation / Markov switching / AIDS model / Maximum likelihood / Hamilton filter / Markov chain Monte Carlo / Gibbs sampler / Multi move sampler |
Outline of Final Research Achievements |
In 2012,we published a paper "Another view of impact of BSE crisis in Japanese meat market through the almost ideal demand system model with Markov switching" in Applied Economics Letters, 19, in which we applied a maximum likelihood estimation of a Markov-switching almost ideal demand system (MS-AIDS) model proposed by Allais and Nichele in 2007. Frustrated with many limitations associated with their method encountered in this paper, we went on to develop a Bayesian estimation for MS-AIDS model and illustrate applicability of our proposed method in simulation as well as in empirical study in a paper "Estimating the Markov-Switching Almost Ideal Demand Systems:A Bayesian Approach," published in Empirical Economics in 2014. Our proposed method overcomes many limitations associated with the method by Allais and Nichele. Notably our model is able to capture the regime shifts of meat demand coinciding with the timing of bovine spongiform encephalopathy (BSE) cases in Japan and US.
|
Free Research Field |
計量経済学
|