Dependency relations among stock market indices using transfer entropy : evidence from Bursa Malaysia / Izzul Adha Mohd Razali

Quite a number of literature exists on networks in finance and most of them are usually related to interbank market to find the correlation between borrowing and lending only. However, there were less studies of dependency between stock market indices. The current study seeks to explain the methods to develop networks of stock market indices using information and correlation based measures. Plus, the aim of the research is to find the best method to determine the correlation between stock index return and different types of industries in Bursa Malaysia. Secondary data were collected from 10 different stock indices in Bursa Malaysia for ten years (2006-2015). Then, the absolute values of stock market indices were used as well as their single-day lagged values to show the correlation and the flow of information from one stock index to another. The formulism of partial correlations was carried out to build the dependency network of data and calculate the partial Transfer Entropy to quantify the indirect influence the indices have on one another. Findings from the current work suggests that Transfer Entropy is an effective way to quantify the flow of information between indices and that a high degree of information flow between indices lagged by one day coincides with the indices on the current day.