Determining the Dependency Pattern of Daily Change (increase or decrease) of Dhaka Stock Exchange Index (DSEX) in Bangladesh by Markov Chain and Logistic Regression Model

Abstract

Bangladesh's capital market is South Asia's third largest market with two stock exchanges controlled by the Securities and Exchange Commission (SEC), namely Dhaka stock exchange (DSE) and Chittagong stock exchange (CSE). DSE introducing DSE broad index (“DSEX”) and DSE 30 index (“DSE30”) that effect from 2013. In this study, DSEX which reflect 97% of the total equity market capitalization is considered and focused the effect of change of index on market investment. The logistic regression (LR) model is performed in conjunction with the Markov chain (MC) of different order to represent the dependence of change (increase or decrease) of the current index upon the change of the previous two-time period. It was shown that the increased index day of the preceding two-time period relative to the decreased index day of the preceding two-time period affects the increased index day of the present time period. We observed a dependency of increase-decrease index of spell for the occurrence of index in the Dhaka stock exchange from the period of 28/01/2013 to 30/04/2019. The result shows that the frequency of index shift follows a second order Markov chain and logistic regression suggests that decrease index day of index followed by decreased and increase day of index followed by increased is more likely for the index of Dhaka stock exchange. This research helps to the individual investors in predicting the next day’s stock price based on the prior two days index price. This study also contributes to researchers, corporate managers and other personnel to determine the dependency pattern of stock price.