Read full paper at: http://www.scirp.org/journal/PaperInformation.aspx?PaperID=53436#.VMWoPyzQrzE Author(s) Yoshihiro Ohtsuka 1 , Kazuhiko Kakamu 2 Affiliation(s) 1 Department of Economics, University of Nagasaki, Nagasaki, Japan . 2 Faculty of Law, Politics and Economics, Chiba University, Chiba, Japan . ABSTRACT A random walk Metropolis-Hastings algorithm has been widely used in sampling the parameter of spatial interaction in spatial autoregressive model from a Bayesian point of view. In addition, as an alternative approach, the griddy Gibbs sampler is proposed by [1] and utilized by [2]. This paper proposes an acceptance-rejection Metropolis-Hastings algorithm as a third approach, and compares these three algorithms through Monte Carlo experiments. The experimental results show that the griddy Gibbs sampler is the most efficient algorithm among the algorithms whether the number of observations is small or not in terms of the c...
Scientific Research Publishing