It is clear that BUSINESS CYCLES are inevitable in economy. On the other hand, the economists are always looking for how to form BUSINESS CYCLES and so under the effect of economic policies, since the economic situation is depended to these policies. Therefore, the access to more precise BUSINESS CYCLES FORECASTING methods would direct and manage the economic situation and policies powerfully. Hence, the main objective of this study is to construct a new model based on Markov-Switching Autoregressive (MS-AR) model to forecast the BUSINESS CYCLES in Iran. In addition, the model constructed is compared to ARIMA to represent its power. GDP data seasonally covers the period 1989: I-2009: IV collected from Central Bank of Iran. MS-AR and ARIMA models are applied to forecast the behavior of BUSINESS CYCLES. By using MAPE, RMSE and Theil criteria (TIC), the results indicate that MS-AR model will work better than ARIMA to forecast GDP BUSINESS CYCLES.

This paper has decomposed, statistically, the real GDP of Iran into three components, long run trend, BUSINESS CYCLES and short-run shocks. This is devoted to the empirical measurement, identification and causes of the BUSINESS CYCLES. It also estimates GDP growth on the basis of estimated trend, BUSINESS cycle and irregular component.The methodology consists of three steps: The first, to dissect the real GDP to get its components, the second, empirical investigation of the BUSINESS CYCLES which involve identification and causes, and the third, to predict the components into future. First is assumed that annual series of real GDP is an aggregate of three components including trend, cyclical movements and irregular movements. The HP filter is used in two stages to separate these components; a) to extract the long run trend from the original series and b) to filter out CYCLES from the rest. Second, the main macro variables are tested in terms of co movement volatility. And finally, the trend and CYCLES into future over a five-year period are estimated using ARIMA.It is found that the trend growth of real GDP is negative, during the periods of 1356-61 and 1364-67 Iranian years. The results also show that the economy of Iran has undergone seven complete BUSINESS CYCLES, and it is now facing the recessionary phase of an eight BUSINESS cycle, which has begun in the early 1380. It is projected that the current recession will continue until 1383 (2004), and then recovery will take place.It is also found that the Iranian economy is cyclical in a BC sense.Statistically, the results show that the GDP CYCLES last, on average, 6 years.We also showed the existence of co movement between GDP and the most relevant macro variables. In other words, the main aggregates are also cyclical and their peaks and troughs occur at more or less the same quarters as the GDP.Finally, the results indicate that investment and exports have an active role in generating CYCLES. Most major finding is that the Iran BCs are caused by shifts in oil revenues. The evidence shows that this variable composes all the characteristics of the typical causes and leads the GDP movements.

BUSINESS CYCLES are repeatable phenomena but they might be different in terms of their domain motion and cycling period. In 1930s, economists attempted to forecast major macro economic variables such as GDP, price levels, unemployment...etc. In this regard, the structure of the combined indicators was watched in particular and econometric techniques were effectively employed in diversifying and expanding such indices. Present paper studies time series of 70 important variables in the Iranian economy relative to GDP. The results advocate that the real oil income and the real imports turning points are several seasons ahead of the GDP in terms of timeliness. At the same time, these variable have upward correlation trend and move in the same dicection. In another phase, a combined index was formed from two leader variables and characteristics of their turning points in the past decades were compared with of GDP. It was asserted that whilst combined indices behaviour is similar to GDP, its turning point is 4025 seasons earlier than the GDP"s. This phenomenon can be exploited to forecast GDP. Also, sutdy shows that during the past decades, the average stagnation CYCLES in Iran were 41 month and of booming were 32 months. In other words, booming CYCLES were consistetly shorter than stagnation CYCLES and on average, the BUSINESS CYCLES of Iran lasted 75 months.