Modeling and Forecasting The Domestic Price Volatility of Coffee in Ethiopia
No Thumbnail Available
Date
2018-06-05
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
Coffee is the most popular globally traded soft drink in the world. Ethiopia is the birth place of Coffee Arabica and remains the largest producer and exporter of coffee in Africa. The aim of this study was to model and forecast the domestic price volatility of coffee in Ethiopia using an appropriate financial time series models. The data used are monthly observations of the domestic price of coffee, food price index, fuel oil price, exchange rate, interest rate etc. from January 2003 to December 2016.
The price return series of coffee has been show the characteristics of financial time series such as volatility clustering, leptokurtic distributions and leverage effects. Thus ARIMA family models for mean equation and GARCH family models for variance equation were employed to model the monthly domestic price volatility of coffee in Ethiopia. Among GARCH family models considered in this study, ARMA (3, 3)-EGARCH (3, 0) model with normal distributional assumption of residuals were found to be a better fit for domestic price volatility of coffee.
Export price of coffee, exchange rate, food inflation rate, nonfood inflation rate and total government revenue were found to have statistically significant effect on average monthly price volatility of coffee. The asymmetric term was found to be positive and statistically significant in EGARCH (3, 0) volatility model for coffee. This is an indication that unanticipated increase in domestic price had larger impact on domestic price volatility than unanticipated decrease in the domestic price of coffee.
Finally, various forecast accuracy measure statistics indicates that the estimated ARMA(3, 3) model is good enough to describe the domestic price of coffee. Moreover, the out-of-sample forecasts indicates that the domestic price of coffee has almost a constant trend. The in-sample forecast using the best-fit asymmetric model, that is EGARCH(3, 3) model indicates that the domestic price volatility of coffee remained at almost a constant level around the begining and ending of the study. But it increased steadily with increasing rate from December 2010 to January 2011, immidiatlly dropes sharply with increasing rate till March 2011.
Description
Keywords
Coffee, Arima, Garch, Forecasting, Ethiopia