Volatility Modelling of Agricultural Commodities: Application of Selected GARCH Models

Abstract

This paper does an empirical analysis of a selection of agricultural commodities, cocoa, coffee and sugar, as well as the currencies of the countries that produce the largest amount of the selected commodities, the Brazilian Real and the CFA Franc. In addition, the S&P GSCI Agriculture Index is included as an indication of overall agriculture prices as a comparison variable. The empirical analysis models the volatility of the variables included in the paper. The data will be evaluated by means of number of financial econometric models. The financial econometric models of the GARCH family models that will be used are the generalised autoregressive conditional heteroscedastic (GARCH) model, the Glosten-Jagannathan-Runkle generalised autoregressive conditional heteroscedastic (GJR-GARCH) model and the exponential GARCH (EGARCH) model. The models will be based on daily data from 1 January 2007 to 23 March 2017, split between the 2007–2009 financial crisis period and the period after the 2007–2009 financial crisis. The results suggest that volatility is present in the data, and therefore the models mentioned will be compared in order to identify which model is the best fitting model for the selected commodities, currencies and index. Overall, GARCH was the best fitting model for the S&P GSCI Agriculture Index during and after the financial crisis and EGARCH for the Brazilian Real. The remainder of the variables had different model results. Only the GJR-GARCH results for cocoa indicated that leverage effects exist which imply that negative shocks have a greater effect than positive shocks.