La robustesse des tests de transmission asymétrique des prix en présence de changements structurels

Asymmetric price transmission, especially between vertically separated markets, has been a subject of considerable attention in agricultural economics. Asymmetric price transmission is not only important because it may point to gaps in economic theory, but also because its presence is often considered for policy purposes to be evidence of market failure. The focus of this paper is on the empirical methods used to determine whether price transmission is asymmetric or symmetric. Specifically, we analyse the behaviour of the common tests for asymmetry in the presence of structural breaks in the underlying data, and we test whether such breaks lead to overrejection of the null hypothesis of symmetric transmission. Hence we test the robustness of such tests. The results of Monte-Carlo experiments demonstrate that in the presence of structural breaks in symmetrically linked price data, tests will tend to reject the null hypothesis of symmetric transmission at the 5% level of significance in considerably more than 5% of a large number of repetitions. In other words, in the presence of structural breaks, the true size of tests for asymmetric price transmission is considerably larger than the chosen significance level. Our results are important for many empirical studies on asymmetric price transmission, because the results emphasise the necessity of test for structural breaks. Otherwise, in the case of undetected structural breaks, the results of asymmetry tests might be missleading.