Modeling Business Cycles with Markov Switching Arma (Ms-Arma) Model: An Application on Iranian Business Cycles

In this paper, the Iran Business Cycle characteristics were investigated via numerous univariate and multivariate Markov-switching specifications. In this case Markov switching model MSM-ARMA is proposed for determining business cycles. We examined the stochastic properties of the cyclical pattern of the quarterly Iran real GDP between 1988 (1) ? 2008 (2). The empirical analysis consists of mainly three parts. First, a large number of alternative specifications were tried and few were adopted with respect to various diagnostic statistics. Then, all selected models were tested against their linear benchmarks. LR test results imply strong evidence in favor of the nonlinear regime switching behavior. In line with the main objective of research, proposed model for Iran business cycle is estimated by and result of this estimation showed that economic of Iran despite of having two periods of recession 1992(3) - 1992(4) and 1995(1)-1995(2), is out of recession with moderate growth and also experienced growth with high rate in early period of studying. Also the possibility of resistance of recession regimes with moderate and high growth is 0.3, 0.92 and 0.5 respectively. The results show the economic tend to stay in moderate growth regime.