This paper examines the evidence for a day-of-the-week eŒect in ® ve Southeast Asian
stock markets: South Korea, Malaysia, the Philippines, Taiwan and Thailand. Find-
ings indicate signi® cant seasonality for three of the ® ve markets. Market risk, prox-
ied by the return on the FTA World Price Index, is not su cient to explain this
calendar anomaly. Although an extension of the risk-return equation to incorporate
interactive seasonal dummy variables can explain some signi® cant day-of-the-week
eŒects, market risk alone appears insu cient to characterize this phenomenon.
Applied Economics Letters ISSN 1350± 4851 print/ISSN 1466± 4291 online # 2001 Taylor & Francis Ltd 155
http://www.tandf.co.uk/journals
156 C. Brooks and G. Persand
in particular, how the risk varies through the week. The X
5
y
remainder of the paper develops as follows. Section II out- Rit ˆ ¬i ‡ i RME t ‡ ®y D it ‡ "it …2†
yˆ1
lines the data and empirical methodology employed.
Section III presents the empirical results, while Section where all terminology is as for Equation 1, and in addition,
IV concludes. RME t is the return on the market portfolio, given by the
return on the FTA World Index, which is used as a proxy
for market risk. Dity are the seasonal dummy variables. If
these dummy variables are insigni® cant where they were
II. DATA AND METHODOLOGY
previously signi® cant for Equation 1, we can say that the
seasonality is in the risk-return relationship. However, if
Stock Indices were obtained from Datastream on a daily
they are still signi® cant, then other risk factors should be
close-to-close basis for all weekdays (Monday to Friday)
considered.
falling in the period 31 December 1989 to 19 January 1996
However, Equation 2 does not consider risk variation on
(a total of 1581 observations), for the following countries,
any particular day, but rather it only gives the variation in
together with the FTA World Price Index: mean returns on each day. In particular, the equation
South Korea: South Korea Stock Exchange Composite forces the risk-return relationship to be constant over all
Price Index days of the week. Hence, in order to look at how risk varies
Malaysia: Kuala Lumpur Composite Price Index across the days of the week, interactive dummy variables
Thailand: Bangkok Stock Exchange Price Index (seasonal dummy variables multiplied by the return on
Taiwan: Taiwan Weighted Price Index FTA World Index) are used to determine whether risk
Philippine: Philippines Stock Exchange Composite increases (decreases) on the day of high (low) returns.
Price Index The risk equation can be written:
X
5 X
5
For each index, a series of daily, continuously com- Rit ˆ ¬i ‡ iy Dyit ‡ ®iy ‰Dyit RME t Š ‡ "it …3†
pounded log returns are calculated in the usual manner. yˆ1 yˆ1
The return on the market index is regressed (separately In this way, when considering the eŒect of market risk on
for each country) on 5 dummy variables, representing each seasonality, we are allowing for risk to vary across the days
day of the week (Monday to Friday), to test for the diŒer- of the week.
ence in the mean rates of return across the days of the
week:
III. RESULTS
Rt ˆ ¬1 D1t ‡ ¬2 D2t ‡ ¬3 D3t ‡ ¬4 D4t ‡ ¬5 D5t ‡ "t …1†
Table 1 gives the results for estimation of Equation 1, that
where, Rt is the log return of the market index, D 1t , is the average returns on each day of the week. The main
D2t ; . . . ; D 5t are the dummy variables representing features are as follows. Neither South Korea nor the
Monday, Tuesday; . . . ; Friday respectively (so that Philippines have signi® cant calendar eŒects;2 both
D1t ˆ 1 if day t is a Monday, zero otherwise and so on), Thailand and Malaysia have signi® cant positive Monday
"t is an iid error term. ¬ to ¬5 represent the mean returns average returns and signi® cant negative Tuesday returns;
for Monday through Friday. 1 Taiwan has a signi® cant Wednesday eŒect. The eŒects of
Although signi® cant coe cients in Equation 1 will sup- incorporating the daily seasonal dummies into the empiri-
port the hypothesis of seasonality in returns, it is important cal market model given by Equation 2, are presented in
to note that risk factors are not taken into account. The Table 2. It is evident that the incorporation of the risk-
possibility that the market can be more/less risky on certain proxy in an additive fashion is insu cient to explain the
days must be allowed for. Hence, low (high) signi® cant day-to-day variation in average returns. In fact, any signif-
returns in Equation 1 might be explained by low (high) icant day-of-the week-eŒects noted from Table 1 still
risk. We thus test for seasonality using the empirical mar- remain after the incorporation of the risk factor, apart
ket model, whereby the market risk is proxied by the return from the negative Tuesday returns in Thailand. It is inter-
on the FTA World Price Index. The market model is given esting to note that the market betas for all three countries
by the following equation, estimated separately for each are considerably less than unity, although all are signi® cant
country I: in their respective regression equations.
1
In order to allow for the possible presence of heteroscedasticity and serial correlation in the "t ’s, the t-statistics in all subsequent analysis are computed
using robust standard errors following Newey and West (1987) and White (1980). Parzen weights are used and the window size is speci® ed as one third of
the available data.
2
South Korea and the Philippines are therefore excluded from subsequent analysis, since there are no signi® cant calendar anomalies to explain.
Seasonality in Southeast Asian stock markets 157
Table 1. Values and signi® cances of days of the week
Notes: Coe cients for Equation 1 are given in each cell followed by t-ratios in parentheses; * and **
signi® cance at the 5% and 1% levels respectively.