TIME SERIES PATTERNS OF SRI LANKAN STOCK RETURNS

Predicting the future was one of the strongest desires of man. The actualization of the desires historically began with astrology paying the path for scientific predictions and forecasting. Scientific forecasting in financial markets also has a long history going back to 1950’s. Literature shows several attempts in modeling share returns in Sri Lankan context, but outcomes of the studies were not satisfactory. Colombo Stock Exchange (CSE) is a population containing 20 mutually exclusive subsets (sectors). Elements of these subsets are homogeneous in nature of business. As such, there may be similarities in market performances within groups and similar forecasting techniques may successful in forecasting. The present study was focused on sector-wise pattern recognition of returns and identifying suitable time series forecasting techniques. A random sample of four business sectors was selected and required data were obtained from the CSE data library, 2011. Box- Plots of returns and one–way ANOVA was used for comparison of returns within and between sectors. Results did not give evidence for significant differences in mean returns. Time series plots of returns of individual companies as well as sectors showed no trends. Stationary of the series were tested by Auto Correlation Functions (ACF’s) and found all the series stationary. Based on the results it was concluded that company returns, as well as sector returns of CSE, were stationary. It is recommended to test ARIMA models and Spectral Analysis in forecasting returns of the Sri Lankan share market