@techreport{oai:tsukuba.repo.nii.ac.jp:00027215,
 author = {KABE, Satoshi and KANAZAWA, Yuichiro and 金澤, 雄一郎},
 month = {Mar},
 note = {Allais and Nich`ele (2007) proposed a Markov-switching almost
ideal demand system (MS-AIDS) model by extending the idea of
Hamilton (1989). This model enables us to determine when the regime
shifts occurred and to estimate parameters characterized across the
different regimes. Moreover, degree of belongingness to each of the
regimes and transitions between regimes are quantified by the probabilities.
In this paper, we propose a Bayesian estimation for MSAIDS
model and illustrate applicability of our proposed method. The
Bayesian estimation has some important advantages. First, it enables
us to avoid the singularity problem suggested by Hamilton (1990,
1991). Second, our proposed Bayesian estimation ensures that transition
probabilities lie between zero and one. Third, Bayesian estimation
is able to avoid the messy calculations entailed in the score
functions of log-likelihood. We then run a simulation study to confirm
the validity of the proposed method. In the empirical study on
the Japanese meat market, we found that our Bayesian estimation
improves the mean squared errors for all meat products over the maximum
likelihood estimation, while successfully capturing the regime
shifts of meat demand coinciding with the timing of Bovine Spongiform
Encephalopathy (BSE) cases in Japan and U.S.},
 title = {Estimating the Markov-Switching Almost Ideal Demand Systems: a Bayesian Approach},
 year = {2012}
}