Smooth transition vector error correction models for the spot prices of coffee

Abstract

The nonlinear behaviour of four coffee price series is examined, that is, unwashed Arabicas (i.e. coffee from Brazil), Colombian Mild Arabicas (i.e. coffee from Colombia), other Mild Arabicas (i.e. coffee from other Latin American countries), and Robusta coffee (i.e. coffee from Africa and Southeast Asia). First is identified the cointegrating relationships and then that these enter the error correction equations in a nonlinear way is shown. The estimates suggest a rather common pattern of nonlinear adjustment for the same variety Arabica coffees.