A General Framework for Testing the Granger Noncausality Hypothesis

Abstract

In this paper, new noncausality tests relying on a general nonlinear framework are proposed and their performance studied by a Monte Carlo experiment and a variety of nonlinear artificial series. Two of the tests are based on a Taylor expansion of the nonlinear model around a given point in the sample space. Yet another test is based on artificial neural networks. The tests appear to be well-sized and have good power properties.