Sell in May and Go Away–
Summer Break also at the Russian Stock Market?
Peter Reichling and Elena Moskalenko*
For a revised version of this paper see:
Gischer, H.; Reichling, P.; Spengler, T.; Wenig, A. (ed.) (2008):
Transformation in der Ökonomie, Wiesbaden, pp 257–267
* Prof. Dr. Peter Reichling (corresponding author–Otto-von-Guericke-University Magdeburg, Chair of Banking
and Finance, Postfach 41 20, 39016 Magdeburg, Germany, phone +49 391 67 18412, e-mail Peter.Reichling@
ww.uni-magdeburg.de) holds the chair of Banking and Finance at the Otto-von-Guericke-University Mag-
deburg, Germany. Elena Moskalenko holds a master’s degree from the German MBA program Moscow.
There is an ongoing discussion if the ‘sell in May’ strategy, that prescribes stock investments
only during the months from September to May, offers a higher profit than a buy-and-hold
strategy throughout the whole year. In the literature, some empirical evidence is particularly
found for several emerging markets. In comparison to the US stock market, we examine the
profitability of the ‘sell in May’ strategy at the Russian stock market and analyse its risk-
return trade-off. Additional emphasis is laid on the persistence of the corresponding returns.
Capital Market Anomaly, Halloween Effect, Russian Stock Market
G11, G14, G15
Sell in May and Go Away–
Summer Break also at the Russian Stock Market?
This is one of the peculiarly dangerous months to speculate in stocks in.
The others are July, January, September, April, November,
May, March, June, December, August, and February.
Mark Twain–The Tragedy of Pudd’nhead Wilson (1894)
The seesaw changes of stock markets are frequently explained with certain sayings. These
rules are like country sayings: They are correct–at least every now and then. Probably, the
most well-known stock market rules is: Sell in May and go away. For example, by googling
‘sell in May’ one finds more than 80,000 entries in the web. The advise is to part in the
spring with stock market investments. The ‘sell in May’ rule is based on the observation that
share prices apparently tend to decrease during the summer months. This is one of the so-
called calendar effects in connection with numerous capital market anomalies. A capital mar-
ket anomaly contradicts the hypothesis of a weak-form efficient capital market.
In the literature there is an ongoing discussion if the ‘sell in May’ strategy offers a significant-
ly higher profit than a buy-and-hold strategy throughout the whole year. For example,
Bouman/Jacobson (2002) found that a strong ‘sell in May’ effect is present in particular in
European countries and emerging markets. However, Sullivan/Timmermann/White (2001)
attributed test results of this effect to data mining. Maberly/Pierce (2004) re-examined the
Bouman-Jacobson result and found that the effect disappeared in the US data after an adjust-
ment for outliers. Lucey/Whelan (2002) in turn obtained significant results for the Irish equi-
Actually, in May 2006 the US S&P 500 index declined by three per cent. At the same time
the Japanese Nikkei 225 index lost nearly nine per cent, the European Stoxx 50 dropped by
five per cent, and the Russian RTS index decreased by 12 per cent. Accordingly, Forbes stat-
ed: “The axiom ‘sell in May and go away’ worked like a charm” (June 6th, 2006). The Econ-
omist regarded the ‘sell in May’ rule “as an explanation of why investors the world over have
been selling shares since May 11th” (May 25th, 2006). The Financial Times reasoned that
“this year, ‘sell in May and go away’ would have been a great strategy” (July 14th, 2006).
Much is and has been presumed about the reasons for this seasonality. The range of rationales
put forth reaches from the weather, according to which human beings are devoted to idleness
in the summer and recover from the exchange hustle and bustle,1 up to the race of institutional
investors, whose portfolio managers perform their asset allocation at the beginning of the year
and compete for the best starting positions. Profits are preferably realized in the middle of the
year and, at the end of the year, only small upturns are needed in order to induce the managers
to purchase, so that they do not chase the market.2 We note that in both cases it is ignored to
some extent that all buyers face sellers who likely have contrary opinions regarding the future
trend of stock prices.
In order to examine if the ‘sell in May’ rule is useful for investing at the Russian stock market
we proceed as follows. In comparison to the US stock market, in section 2 we analyse if an
investment strategy, which omitted the summer months, was particularly favorable at the Rus-
sian stock market. Subsequently, we fix May as the exit month and look for the best month to
enter the stock market. In section 3, we regard single months in order to determine the strate-
gy which optimally took seasonalities into consideration. Section 4 analyses the risk-return
trade-off of exit-in-May investments as well as the persistency of ‘sell in May’ returns. Sec-
tion 5 concludes with a brief summary.
2 Optimal Annual Entry and Exit Months
The ‘sell in May’ strategy initially leaves us alone with the question about the most beneficial
entry time. But the British know: ...and come back on St. Leger's Day. This is in the middle
1 For rationales in this regard see, e.g., Bouman/Jacobsen (2002) and Garrett/Kamstra/Kramer (2005).
2 In this line of argumentation see, e.g., Wermers (2003) and Doeswijk (2005).
of September. Therefore, one version of our stock exchange rule reads: sell in May and go
away, but remember to come back in September.3 And indeed, relying on monthly S&P 500
returns from 1960 to 2006 (figure 1, left axis) the investment strategy to enter the stock mar-
ket at the end of September and to exit end of May performs best amongst the ones with a
duration of eight months.
Sep-May Best of 8-Months
Duration Stock Investments?
Fig. 1: Average Returns of Stock Investments with 8-Months Duration
If this observation was a universal rule which could then be applied to the Russian stock mar-
ket, figure 1 (right axis) would answer as follows: from 1995 to 2006 we find the highest
average return of the RTS index on US dollar basis for the October to June strategy. 4 ‘Sell in
May’ ranks second highest. This strategy promised nearly eight per cent at the US stock mar-
ket on the 47 years average and even nearly 40 per cent per year at the Russian stock market
during the past 12 years.
If we insist on the ‘sell in May’ rule, which appears more or less valid, what would then actu-
ally be the best time for a re-entry? Again, our stock market rule seems to prove true, because
for both, the US stock market (figure 2, left axis, database as above) and the Russian stock
market (right axis), it was optimal to enter at the end of September, given one wanted to exit
end of May. Note, that intermediate investments remained unconsidered. Thus, we simply
3 Some studies found similar results for an entry at the end of October. Therefore, the supposed profitabil-
ity of the ‘sell in May’ strategy is also known as the Halloween effect, see, e.g., Jacobson/Visaltanachoti
4 The RTS time series only goes back to 1995.
assumed that investors spent their money or put it into the piggy bank during the intermediate
Optimal Stock Marke t Entry in Sep?
Month of Entry
Fig. 2: Average Returns of ‘Sell in May’ Strategies
3 Monthly Returns
A view at the monthly returns shown in figure 3 gives comprehensive information on the most
beneficial entry and exit times. Only in September the S&P 500 return was negative on aver-
age (left axis). Further, it is worth noting that on average the return was below the money
market rate in February and also from May to August. Therefore, the optimal investment
strategy would be to enter at the end of September and to exit end of April with a break in
February. The pattern is different for the RTS index (right axis). Here, the return in May and
from July to September was negative on average during the past twelve years. In November,
it was, on average again, better to hold bonds. Hence, the recommendation would read: enter
at the end of September and exit end of June with stopovers in November and May.
5 Our findings are not strongly affected if we, after the moratorium for foreign debt of the Russian govern-
ment in 1998, take interbank interest rates as a proxy for risk-free returns into consideration. Without any
fixed-income investments in the meantime, during-the-period returns in our figures correspond to annual-
Decreasing Share Prices
Fig. 3: Average Monthly Returns
In fact, significant differences in monthly returns arise in particular cases. Table 1 merely
contains combinations, where such significant differences occurred. It is worth noting that,
for the S&P 500 index as well as for the RTS index, the average September return is statisti-
cally significantly different from the mean returns of five and four other months, respectively.
In this respect, the advantage of the ‘sell in May’ strategy is not primarily based on the exit
time at the end of May, but on the re-entry time end of September.
P-values S&P 500 RTS (USD)
Sep Nov Dec Sep Dec
Jan 2.3 %
Feb 3.8 % 1.6 %
Mar 3.7 % 2.9 %
Apr 2.7 % 2.5 %
Jun 3.3 %
Sep 1.0 % 0.3 % 2.0 %
Tab. 1: Significant Differences in Monthly Returns
4 Risk-Return Trade-off
Today even private investors are familiar with the no risk, no fun principle, according to
which a higher return cannot be expected without bearing additional risk. The range of histor-
ical September to May returns is accordingly large. Figure 4 shows that, based on the S&P
500, returns range from minus 20 to above 40 per cent during the 47 years we covered in our
analysis. The range for the RTS is clearly wider, ranging from below minus 60 to almost 130
per cent during the past 12 years.
Low-risk Sep-May Investments?
Fig. 4: Risk of September-to-May Investments
The broad distribution of ‘sell in May‘ returns leads us to the question if the September-to-
May strategy dominates other exit-in-May strategies with different re-entry months. Figure 5
illustrates the risk-return trade-offs of these strategies. Both, mean return and volatility, tend
to increase with the duration of the stock investment until the September-to-May duration of
eight months is reached. Afterwards, mean returns tend to decline with roughly stable volatil-
ities. This observation holds for both, the US and the Russian stock market. Again, the ‘sell
in May’ strategy appears to be more beneficial than the buy-and-hold strategy of a stock in-
vestment during the whole year. Nevertheless, the return of the September-to-May strategy
on average is for both, the US and the Russian stock market, statistically not significantly
above the average return of an exit-in-May strategy with an earlier entry month.6
6 P-values for one-tailed tests are above 26 and 37 per cent for the S&P 500 and the RTS time series, re-
Exit-in-May Investments‘ Performance
0% 5% 10% 15%
0% 20% 40% 60%
S&P 500 RTS (USD)
Fig. 5: Risk and Return of Exit-in-May Investments
A trading rule is only helpful for an investor if she or he may rely on its constancy. There-
fore, in the following we analyse if from a high September-to-May return in one year we can
refer a similar return next year. Figure 6 visualizes that no such persistency of ‘sell in May’
returns exists. Rather, the September-to-May returns are negatively correlated,7 so that high
returns of our regarded strategy in one year tend to be followed by low returns in the next
year. However, this result is again not statistically significant. All in all, this result brings our
stock market rule back to the level of a country saying.
Persistence of Sep-May Returns
Fig. 6: Persistency of September-to-May Returns
7 The coefficient of autocorrelation of the ‘sell in May’ returns amounts to 0.15 and 0.33 for the S&P
500 (figure 6, left axis) and the RTS (right axis) time series, respectively.
‘Sell in May and go away’ likely represents the most well-known stock market saw. Surpris-
ingly, the saying seemed to prove true for both, the US and the Russian stock market. Based
on the S&P 500 index from 1960 to 2006 and the RTS index on US dollar basis from 1995 to
2006, the September-to-May strategy performed best and ranked second-best, respectively,
amongst stock investments with a duration of eight months. The analysis of single month
returns showed that the advantage of this strategy is predominantly due to the entry time at the
end of September. The exit time end of May comes second.
In addition, the ‘sell in May’ strategy offered a higher risk-return trade-off than exit-in-May
strategies with a longer investment period. However, the ‘sell in May’ strategy unfortunately
turns out to be risky, in particular as soon as an investors from the observation that ‘sell in
May’ worked one year refers that high returns are assured also next year. There is utterly no
evidence for such persistency.
Bouman, S.; Jacobsen, B. (2002): The Halloween Indicator, “Sell in May and Go Away”:
Another Puzzle, American Economic Review 92, 1618–1635.
Doeswijk, R.Q. (2005): The Optimism Cycle: Sell in May, IRIS (Rabobank/Robeco) Working
Garrett, I.; Kamstra, M.J.; Kramer, L.A. (2005): Winter Blues and Time Variation in the Price
of Risk, Journal of Empirical Finance 12, 291–316.
Jacobson, B.; Visaltanachoti, N. (2006): The Halloween Effect in US Sectors, Working Paper.
Lucey, B.M.; Whelan, S.F. (2002): A Promising Timing Strategy in Equity Markets, Journal
of the Statistical and Social Inquiry Society of Ireland 31, 74–110.
Maberly, E.D.; Pierce, R.M. (2004): Stock Market Efficiency Withstands another Challenge:
Solving the “Sell in May/Buy after Halloween” Puzzle, Econ Journal Watch 1, 29–46.
Sullivan, R.; Timmermann, A.; White, H. (2001): Dangers of Data Mining: The Case of Cal-
endar Effects in Stock Returns, Journal of Econometrics 105, 249–286.
Wermers, R. (2003): Is Money Really “Smart”? New Evidence on the Relation Between Mu-
tual Fund Flows, Manager Behavior, and Performance Persistence, Working Paper.