The Designing Early Warning System of Financial Crisis Outbreak in Tehran Stock Exchange by Logit & Probit Model

Encountering with financial crises of supervision and predicting such these events which are necessary to decrease their negative effects on finanicial and economical markets. The current paper is aimed to review the designing the early warning system of financial crisis outbreak in Tehran stock Exchange. Due to this purpose, it’s used the weekly datas during the years from 1997 to 2019 (1121 weeks). The mean of crises in this present papper is the falling more than 15% of price index (TEPIX) toward last three months. Hence, it’s been used the dummy variable for operating the dependent variable. It’s been used the residual of auto regressive integrated moving average (ARIMA) for measuring the shocks caused by the price of stocks, exchange rate, price of oil and gold. The result is modeled by Logit & Probit model and showed that probability of the crisis outbreak is increased by decreasing the stock price in past period as well as the outbreaking of crisis in past period after reviewing and analyzing the data. While the decreasing of exchange rate, increasing of the gold price, and decreasing of oil price don’t affect on crisis outbreak in current periods as meaningfully. Based on weekly data, 44 crisis has occurred which both models have predicted 36 crisis. The power of crisis predicting is 82% and the power of predicting for total model is about 99%.