Abstract:
This report contains the analysis of secondary values of US dollar foreign exchange
rate (LKR per USD), Gold price (LKR per Troy ounce), Oil price (LKR per barrel),
Silver price (LKR per Metric Ton), and Stock return (All Share Price Index) in Sri
Lanka. The purpose of this study is to find the relationship among these variables
and forecast the US dollar foreign exchange rate in Sri Lanka. This study has used
the EViews8 data analysis package to develop time series models to identify the
significance of the relationship between exchange rate and other factors using
monthly data from October 2000 to December 2019. Log transformed first
differenced series were used in Autoregressive Conditional Heteroskedasticity/
Generalized Autoregressive Conditional Heteroskedasticity modeling. The best
model fits for the exchange rate was an exponential GARCH model with EGARCH
(2,2). All variables were significant at the 5% level of significance and free from the
serial correlation/ heteroskedasticity. The model is sufficient but residuals are not
normal. Finally, USD forecasting was done for January to December 2019 using the
best fitted model. The mean average percentage error value (5.27%) is in between
the highly accurate range (0%-10%).
Citation:
Shanika, M.H. (2022). Modelling exchange rate of USD to Sri Lankan rupees with oil prices, gold prices, silver prices and return of all share price index of Sri Lanka [Master's theses, University of Moratuwa]. Institutional Repository University of Moratuwa. http://dl.lib.uom.lk/handle/123/22533