Time Series Forecasting of Daily Gold Prices in Pakistan

This study identifies the major determinants of gold price forecasting and checks the short-run and long-run relationship along with US-Dollar prices in Pakistan. The data set covers daily observations over the period 2007 to 2018. To examine the relationship between gold price and US-Dollar price, ARIMA, ARDL and ADF model has been used. The Gold price is the variable of interest, whereas the explanatory variable is US-Dollar. The finding of the study indicates that the value of the gold price co-integrated at zero order of interaction, which means that the gold price is stationary at the level and the value of the US-Dollar is not co-integrated there for it is non-stationary at the level, but it become stationary by taking 1st difference. The result also postulated that ADF is more precise to check the short run and long run relationship between gold price and US-Dollar price. There exists long run and short run relationship between gold price and US-Dollar and also ARIMA model is used for the forecasting purpose. ARIMA model is one of the best techniques for the selection of good model. Study shows that ARIMA (3, 0, 1, 1) is a good model.