This paper derives a sufficient condition for noncausality at all forecast horizons (infinitestep noncausality). We propose a test procedure for this sufficient condition. Our procedure presents two main advantages. First, our infinite-step Granger causality analysis is conducted in a more general framework with respect to the procedures proposed in literature. Second, it involves only linear restrictions under the null, that can be tested by using standard F statistics. A simulation study shows that the proposed procedure has reasonable size and good power. Typically, one thousand or more observations are required to ensure that the test procedures perform reasonably well. These are typical sample sizes for financial time series applications. Here, we give a first example of possible applications by considering the Mixture Distribution Hypothesis in the Foreign Exchange Market
 

---

Download from REPEC

Download from SSRN

---