The Application of Garch Family Models to Some Agricultural Crop Products in Amhara National Regional State

Abstract

The price volatility of agricultural crop products has increased in the last decade. It has a negative impact on the economy of the country through income instability for producers, consumers and whole sellers and also leads to a major decline in future output. The aim of this thesis is to identify and analyze the determinant factors of average monthly price volatility of cereals (wheat and barley) and pulses (bean and pea) in Amhara National Regional State over the period of December 2001 to June 2012 GC. The return series considered exhibited typical characteristics of financial time series such as volatility clustering, leptokurtic distributions and asymmetric effect and thus, can suitably modeled using GARCH family models. Among such models entertained in this study, ARMA(1,0)-EGARCH(3,3) with GED for wheat, ARMA(4,4)-EGARCH(2,3) with GED  for bean and ARMA(1,0)-EGARCH(1,2) with student-t for pea were chosen to be the best fit models. The monthly price return series of barley exhibited no ARCH effects, and thus, was not modeled using (G)ARCH family models. From the results, exchange rate and general and food inflation rates were found to be an increasing effect on price volatility of wheat, bean and pea. On the other hand, rainfall was found to have a stabilizing effect on the price volatility of these crops. Moreover, saving interest rate has a decreasing effect on the price volatility of wheat and bean. The results also revealed that price volatility has seasonal variation. The asymmetric terms were found to be significant in all GARCH models considered. Thus, price volatility tends to over-react in response to bad news as compared to good news. Furthermore, the significance of the EGARCH terms provides strong evidence of volatility spillover from one period to another.

Key words: price volatility, crop products, ARMA, ARCH, GARCH family models