Global Journal of Human Social Science, E: Economics, Volume 23 Issue 2

Volume XXIII Issue II Version I 55 Global Journal of Human Social Science - Year 2023 ( )E © 2023 Global Journals Impact of COVID-19 on Stock Market Volatility and Forecast using ARIMA and EGARCH 1,600 2,000 2,400 2,800 3,200 3,600 IV I II III IV I II III IV I II III IV I 2017 2018 2019 2020 Stock Exchange Composite Index Figure 1: Historical Plots of GSECI The plot of the historical daily GSECI shows that the series is trending downwards and not reverting to its mean. By visualizing it, we say the series is non- stationary. fluctuates around some common mean and therefore it is non-stationary. This is confirmed with the use of the Dickey- Fuller test for unit root presented in Table 1. a) Unit Root Test for Stationarity Table 1: ADF test statistics IGSECI I (0) I (1) t-Statistic P-value t-Statistic P-value AIC -3.366978 0.0566 -5.599723 0.0000 SIC -3.242959 0.0769 -6.149055 0.0000 HQC -3.366978 0.0566 -5.599723 0.0000 Table 1 presents the test for unit roots of the series using all the criteria (i.e. Akaike Information Criterion, Schwarz Info Criterion, and Hanna-Quin Criteria). For all the criterion at the intercept and trend, it is found that the daily series of Ghana Stock exchange composite index for the period under study is not stationary at 5% level and therefore the series must be transformed. It is confirmed by using a correlogram. With the aid of a correlogram, we check for stationarity. In Appendix 1, it is found that the series is not stationary at level since the ACF declines very slowlyup to about 36 lags. It showed a significant autocorrelation that is outside the error bounds and decays slowly. It is indicative that the series is nonstationary since they are outside the standard error bounds or confident interval at 95%. The PACF also drops immediately after the first and second lag continuously. The series is therefore not stationary.