Cointegration Based Regression to Analyse Linkage between Share Price Index and Macroeconomic Variables: Evidence from Colombo Stock Exchange

Abstract

The main objective of the study is to investigate the long run performance of the All Share Price Index (ASPI) of the Colombo Stock Exchange, based on the economic activities of Sri Lanka using cointegration and auto regressive time series. The cointegration test illustrates that share price index is cointegrated with a specific set of macroeconomic variables, i.e. exchange rate (USD/LKR), money supply, wage rates, wet foreign assets, currency in circulation, imports and exports with 95% confidence. The study also proposes a regression model using Eigen Vector coefficients to predict the behavior of ASPI index in the long run. The model performance, evaluated using the residuals of the test data, represents a random behavior indicating a valid long-run cointegration regression relationship between ASPI and other macroeconomic variables. Future studies involve analysis of the short-run relationship among the macroeconomic variables using Vector Error Correlation Model.