Does Change over Time the Causal Relationship between Economic Growth and Foreign Trade in Turkey?

This paper investigates the relation between economic growth, export growth, and import growth in Turkey using time-varying causality methods. The starting point in examining the causality relationship is Granger's study in 1969. Granger's (1969) causality study does not consider structural changes or breaks because it examines the sample period as a whole. For this reason, traditional Granger causality analysis cannot determine changing causality relations when structural changes or breaks occur in the sample period. Therefore, this study uses the time-varying parameters and the recursive evolving window causality methods. First, a traditional Granger causality analysis applied for the entire sample period shows a bidirectional causality relationship between import growth and economic growth. Subsequently, the paper examines the time-varying parameters causality method that has robust statistics. Finally, it evaluates the consistency under the heteroscedasticity recursive evolving window causality method. The results of the parameters of the discussed causality relationships change over time. Further, numerous causality relationships corresponding to certain crisis periods are reached from economic growth to export growth and import growth and from export growth and import growth to economic growth. Both time-varying parameters and recursive evolving window causality methods confirm the reflection of the causality relationship between the variables when structural changes occur in Turkey. Consequently, the authors used two different causality methods to identify the inadequacies of the traditional Granger causality method and determine the periods of changing causality relations in Turkey