Testing for causality in the presence of leading variables

• Autores: Theologos Pantelidis
• Localización: Economics and Business Letters, ISSN-e 2254-4380, Vol. 4, Nº. 1, 2015, págs. 17-29
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • This paper provides useful guidelines to practitioners who investigate causality-in-mean and/or causality-in-variance within a trivariate system by means of the two-step procedure proposed by Cheung and Ng (Journal of Econometrics, 1996) and modified by Hong (Journal of Econometrics, 2001). Specifically, this study highlights cases that can mislead the researcher into reporting false causal relations among the variables under scrutiny. The results of Monte Carlo simulations reveal the seriousness of the problem. Finally, an empirical application that investigates causality-in-mean among three major European stock markets illustrates the proper procedure to follow for correct inference.