An Empirical Study on Day of the Week Effect; Evidence from Colombo Stock Exchange

Abstract

Seasonalities in security market returns have been extensively documented. Among the different seasonal effects observed in stock markets, an interesting one is the seasonality across days of the week. Fields (1991) observed that the US stock market consistently experienced significant negative and positive returns on Mondays and Fridays respectively. This matter was further tested in 1980’s (French, 1980; Gibbons and Hess 1981, Lakonishok and Levi 1982). The capital markets of many other countries also experience the similar seasonality (Jaffe and Westerfield 1985, peiro 1994, Agarwal and Tando 1994). This day of the week effect is a sharp contrast to the efficient market hypothesis. This study examines the day of the week effect in the Colombo Stock Exchange using the All Share Price Index (ASPI) and the Milanka Price Index (MPI). The study covers the period from 1985 to 2004. We compute the returns of the above market indexes as daily price relatives and log returns are taken for the study. To estimate day of the week effect in return, we use the ordinary least square (OLS) equation. In the equation index returns are taken as the dependent variable and five dummy variables are inserted as independent variables from Monday to Friday. We estimate the day of the week effect for the total sample period and revealed that there is no any significant day of the week effect in the total period. Then we analyzed the day of the week effect in five year sub samples and results are similar to the total sample period except in the last sub sample that is from 2000 to 2004. In the last sub sample there is a statistically significant Friday effect and for other days, returns are not significant.