ABSTRACT
In this article, we study the movement between cocoa and coffee prices, two close substitute commodities. Using the ARDL approach developed by Pesaran et al. (2001), we found that the two prices are cointegrated. The long-run elasticity of coffee price with respect to the cocoa one is estimated at 0.88. Also, using the lag-augmented VAR approach of Toda and Yamamoto (1995), which is valid whatever the order of integration of the data, the cocoa price is found to granger cause the coffee price and not vice versa. This finding suggests that models aiming at forecasting coffee prices should incorporate cocoa prices as well.
KEYWORDS:
Disclosure statement
No potential conflict of interest was reported by the authors. The opinions expressed here belong to the authors, and do not necessarily reflect those of PIM, IFPRI, or CGIAR.
Supplemental data for this article can be accessed here.
Notes
1 Even if the two commodities may not be produced in the same area in a particular country.
2 The Granger causality analysis will help address this issue (see next section).
3 We are grateful to an anonymous referee for pointing this out.
4 Here we have an ARDL (1,0) model.