Content uploaded by Venus Khim-Sen Liew
Author content
All content in this area was uploaded by Venus Khim-Sen Liew on Apr 21, 2016
Content may be subject to copyright.
The Empirical Economics Letters, 14(2): (February 2015) ISSN 1681 8997
The Day-of-the-week Effect in the Hang Seng Index
Ricky Chee-Jiun Chia
Universiti Malaysia Sabah, Malaysia
Venus Khim-Sen Liew
Universiti Malaysia Sarawak, Malaysia
Syed Azizi Wafa Syed Khalid Wafa
Universiti Malaysia Sabah, Malaysia
Abstract: This study finds the existence of Friday effect in the return of Hang Seng
Index. This finding implies that the Hong Kong Stock market is inefficient with respect
to price information. Besides, the Hang Seng Index returns are predictable and hence
profitable trading strategies can be developed. Thus, investors could use the day-of-
the-week effect information when investing in the Hong Kong stock market.
Keywords: Day-of-the-week-effect; Hang Seng Index
JEL Classification Number: G12, C32
1. Introduction
The day-of-the-week effect is a stock market phenomenon in which the observed average
daily stock return of certain day(s) is consistently different from the other days of the
week. Empirical studies have found that the day-of-the-week effect appears not only in the
United States, the biggest capital market of the world and in other developed markets such
as United Kingdom, Germany and Japan, but also in many emerging markets. See for
instance, Gibbons and Hess (1981), Keim and Stambaugh (1984), Rogalski (1984), Jaffe
and Westerfiled (1985), Arsad and Coutts (1996), and Apolonario et al. (2006) for
empirical studies on developed markets. On the other hand, Wong et al. (1992), Clare et
al. (1998), and Kok and Wong (2004), Brooks and Persand (2001), and Hui (2005), among
others, deal with the emerging markets. Among those emerging markets, one of the most
appealing markets is the Hong Kong stock market. It is well known for its open yet
regulated policies on the securities industry. Besides, it has sound technical market
infrastructure, as well as corporate governance (Ghosh, 2006). Apart from that, the Hong
Kong’s ideal geographical location, high-speed communications, the free flow of
information, no restriction on capital flows and the world’s freest economy system enable
its market to grow as a strategic stock market for international investors. In fact, Hong
Kong was the Asian’s largest fund raising center for the few consecutive years since 2004.
The Empirical Economics Letters, 14(2): (February 2015) 108
As of the end of the year 2006, a total of 1156 companies with a market capitalization of
US$1.7 trillion were listed on the Stock Exchange of Hong Kong. According to the
International Business and Financial Centre, Hong Kong’s stock market is the world’s
sixth largest and Asia’s second largest in term of market capitalization, as of January
2007. Due to the importance of this market to investors, this study examines the existence
of day-of-the-week effect in the Hong Kong stock market.
2. Data and Method
The data of this study consists of the daily closing values of the Hang Seng Index (HSI),
the major Hong Kong stock index, over the period 1st January 2000 to 31st December
2006. HSI is a capitalization weighted stock market index in the Hong Kong Stock
Exchange. It is used to record and monitor daily changes of the largest companies of the
Hong Kong stock market and as the main indicator of the overall market performance in
Hong Kong. When HSI was started published 40 years ago, its base of 100 points was set
equivalent to the stocks’ total value as of the market close on July 31, 1964. As of
December 28, 2006, it passed the 20,000 point milestone. These dates were chosen based
on the studies of Jang and Sul (2002) which noted that the post crisis period starts from
February 1, 1998 toward. However, to avoid our results affected by the crisis period,
therefore, we examined this study start from year of 2000.
Following the literature, daily returns are calculated as the first difference in the natural
logarithms of the stock market index. The following adjusted return was used (Koop,
2006):
)/ln(100 1
ttt IIR
(1)
where
t
I
and
1t
I
are the values for each index for periods
t
and
1t
, respectively. In
the case of a day following a non-trading day, the return is calculated using the closing
price indices of the latest trading day.
This study employs the following ordinary least squares (OLS) model with dummy
variables to test for the daily seasonality in stock market adjusted:
t
4
1i
k
1i iti4iti0t RR
(2)
where
t
R
is the logarithmic return of the market index at day t;
it
R
is the logarithmic
return of the market index at day t –i;
t3t2t1 ,,
and
t4
are dummy variables which
take on the value 1 if the corresponding return for day
t
is a Tuesday, Wednesday,
Thursday and Friday respectively and 0 otherwise;
t
is the error term. Meanwhile,
The Empirical Economics Letters, 14(2): (February 2015) 109
k0 ,...,
are parameters to be estimated. Among them,
0
measures the mean return (in
percentage) on Monday; whereas
41,...,
capture the difference of average return of the
stock index for Tuesday, Wednesday, Thursday and Friday respectively as compared to
the Monday’s mean return.
A lagged value of the return variable was introduced in the Equation (2) to avoid serial
correlation error terms in the model, which may yield misleading inferences. Besides,
Monday dummy variable was excluded from the equation is to avoid the dummy variable
trap.
3. Empirical Results and Discussions
A number of points emerge from an analysis of the descriptive statistics. First, it shows a
tendency for the lowest mean return to be on Monday and the highest mean return on
Friday. This result is consistent with most previous studies for the day-of-the-week effect.
In contrast to the mean returns, the standard deviation of returns generally is inconsistent
to the portfolio theory associates higher risk with higher returns. When the highest return
in Friday (0.1106%), the standard deviation seems to be the second lowest (1.1556%)
among the days. The null hypothesis of the Jarque-Bera normality test is rejected implies
that daily returns are not normally distributed.
Table 1: Descriptive Statistics of Daily Data
Overall
Monday
Tuesday
Wednesday
Thursday
Friday
Mean
0.0076
-0.0443
0.0222
-0.0188
-0.0315
0.1106
Std. Dev
1.2736
1.3918
1.1166
1.4053
1.2704
1.1556
Skewness
-0.4447
-0.8205
0.4271
-1.0202
-0.0802
0.1214
Kurtosis
7.5382
8.2208
4.4624
10.1497
4.6142
5.1198
Jarque-Bera
1625.3320
455.4873
43.6221
840.7446
40.0202
69.2343
Probability
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
Mean Return
per unit of Risk
0.0059
-0.0318
0.0199
-0.0134
-0.0248
0.0957
Table 2 presents the OLS results for the day-of-the-week effect in this study. The results
show that the coefficient of intercept term that represents the benchmark day of Monday is
insignificant in Hong Kong stock market. The coefficients of the dummy variables for the
day of Tuesday, Wednesday and Thursday are positive but statistically insignificant.
However, the positive Friday returns are statistically significant at 10% level. This Friday
effect seems to be the highest returns as compared to other days in Hong Kong stock
market.
The Empirical Economics Letters, 14(2): (February 2015) 110
Table 2: OLS Results for Day-of-the-week Effect
Parameter
Hong Kong
Constant,
0
-0.0473 (0.4738)
Tuesday,
1
0.0800 (0.3918)
Wednesday,
2
0.0443 (0.6348)
Thursday,
3
0.0278 (0.7656)
Friday,
4
0.1541*** (0.0987)
Return (-1),
5
0.0191 (0.4161)
Return (-2),
6
-0.0290 (0.2148)
Return (-3),
7
0.0310 (0.1819)
Return (-4),
8
0.0206 (0.3757)
Notes: *, ** and *** denote significant at 1, 5 and 10% levels respectively. Numbers in parentheses
depict p-values.
4. Concluding Remarks
This study finds that the Friday’s return is significantly different from other days in Hong
Kong stock market over the sample period of study. The finding of Friday effect could
have useful implications for trading strategies and investment decisions. Among others, it
implies that (i) the Hong Kong Stock market is inefficient with respect to price
information, (ii) the Hang Seng Index returns are predictable and (iii) profitable trading
strategies can be developed (Engle, 1993). Nevertheless, the diagnostic results (not shown
in Table 2 to conserve space) reveal the inadequacy of OLS model as there are remaining
ARCH effects due to the untreated volatility of the returns in the model for the study.
Therefore, such volatility needs to be modeled in order to provide a clearer picture of the
seasonal anomalies in the stock markets. However, it is beyond the scope of this study and
the authors reserved it for a separate study.
References
Apolinario, R.M.C., O.M. Santana, L.J. Sales and A.R. Caro, 2006, Day of the Week
Effect on European Stock Markets, International Research Journal of Finance and
Economics, 2, 53 – 70.
Arsad, Z. and J.A. Coutts, 1996, The Weekend Effect, Good News, Bad News and the
Financial Times Industrial Ordinary Shares Index: 1935 – 94, Applied Economics Letters,
3, 797 – 801.
The Empirical Economics Letters, 14(2): (February 2015) 111
Brooks, C. and G. Persand, 2001, Seasonality in Southeast Asian Stock Markets: Some
New Evidence on Day-of-the-week Effects, Applied Economics Letters, 8, 155 – 158.
Clare, A. D., M.S.B. Ibrahim and S.H. Thomas, 1998, The Impact of Settlement
Procedures on Day-of-the-week Effects: Evidence from the Kuala Lumpur Stock
Exchange, Journal of Business Finance and Accounting, 25, 401 – 418.
Engle, R. F., 1993, Statistical Models for Financial Volatility, Financial Analysts Journal,
49, 72 – 78.
Gibbons, M. R. and P. Hess, 1981, Day of the Week Effect and Assets Returns, The
Journal of Business, 54, 579 – 596.
Hui, T. K., 2005, Day-of-the-week Effects in US and Asia-Pacific Stock Markets during
the Asian Financial Crisis: A Non-Parametric Approach, The International Journal of
Management Science, 33, 277 – 282.
Jaffe, J. and R. Westerfield, 1985, The Weekend Effect in Common Stock Returns: The
International Evidence, Journal of Finance, 40, 433 – 454.
Jang, H. and W. Sul, 2002, The Asian Financial Crisis and the Co-movement of Asian
Stock Markets, Journal of Asian Economics, 13, 94 – 104.
Keim, D. B. and R. F. Stambaugh, 1984, A Further Investigation of the Weekend Effect in
Stock Returns, Journal of Finance, 39, 819 – 835.
Kok, K. L. and Y. C. Wong, 2004, Seasonal Anomalies of Stocks in ASEAN Equity
Markets, Sunway College Journal, 1, 1 – 11.
Wong, K. A., T. K. Hui and C. Y. Chan, 1992, Day-of-the-week Effect: Evidence from
Developing Stock Markets, Applied Financial Economics, 2, 49 – 56.
