Predicting Sectoral Stock Volatility in Amman Stock Exchange Using Various Approaches

There are a numerous number of methods that can be used in financial markets to forecast in the literature; the prominence of predicting is to give the investment community the ability to build their prospect vision decisions about the future expectations, assets allocation, portfolio management, assets pricing and other benefits. This study presents the Autoregressive Moving Average model, Generalized Autoregressive Conditional Hetroscedasticity models, and Vector Autoregressive model which are from the most important forecasting mechanisms that we can use, in financial time series data. The main aim of this study is to predict the volatility of Amman Stock Exchange as one of the emerging markets for the banking sector index volatility using ARIMA model, insurance sector using GARCH models, and the role of oil price in financial sectors performances in ASE by using VAR model. Firstly, we check the stationarity by using unit root test which indicates that there is a stationarity at level for all sectors banking, insurance, and financial sectors. Secondly, the resulted models for this study for banking sector volatility is: ARIMA (0, 0, 1), CGARCH model is the best for insurance sector volatility. Finally, there is no interaction between international oil prices and financial sectors in ASE according to VAR model. Keywords: Financial Markets, Volatility, ARIMA, GARCH, VAR