Testing Causality

TITLE:

A Structural Approach for Testing Causality: An Empirical Investigation

ABSTRACT:

Causality is one of the most important concepts in economics while doing empirical analysis but it is not easily detected. Therefore, it is always important that one should not only investigate the problems only on statistical grounds but also add extra statistical information which may come from economic events happening over a time about the problem under study. This extra statistical information helps in introducing asymmetry in the relationship. Most of the researchers misused Granger causality and assumed that computer run simple set of regression equations results are sufficient to determine the causal direction. In this paper we propose a method for detecting structural causality which is based on extra statistical information, economic theory and statistical analysis. We apply this technique to a simulated data and also apply it to the export-led growth hypothesis for India and Energy-Growth data for Shanghai. Our results indicate that there is unidirectional causality from export to economic growth and no causality between energy-growth variables.

REFERENCE:

By Zahid Asghar and Dr.Asad Zaman