Sensex: Quantifying Sell in May

There is a very famous investment philosophy to Sell in May and return in October.

Lets see how that strategy works for our Indian Markets.

The conditions are to Sell on first day in May and Buy on first day on October with commissions of 5 bps.
We are testing this from year 1980 and 2010 so that it covers most of the history available.

How are the results? Well, its not profitable. The initial equity of $10K got reduced to $9.8K while buy and hold was massively up by ~2 times.

Here's the snap shot of the performance.

There were only 10 profitable years among the 31 years of testing with the year 2010 contributed massively $4780  to the results.
The profits are completely skewed by a single year.

This clearly shows that the strategy is not profitable in itself but there was one profitable trend. That was the higher probability of a dip in early May which lasts for 2-3 weeks on an average.

Here's the equity graph.

India: Analysing January effect on year

January barometer is most discussed for predicting the year end returns for any index.

Lets analyze the January effect on Indian markets. Although the Sensex does not century old data so that we can draw some conclusion with large set of numbers so lets see whatever we can find out with the 30 years of data.

The preliminarily data shows correlation of 0.23 with R square at 0.054 which is quite weak for making any direct statistical analysis. This is evident from the following chart also. There are large number of outliers from the linear trendline.

Going further lets apply some filters and see if we can good data coorealtions. The first filter can be of bands of price change and then finding the probability. Following is the analysis:

The probability of  having a bullish year for a negative January is at 62% which is quite high. But wait.

The last 2 rows shows show the returns with price filters. And both of them have very less probability of bullish year.
The Jan 2011 had -11% returns so the last row shows bullish year has chances of 25% with average change of last occurrences at -11% which is quite bearish figure.

Nifty December seasonal trend

Testing December Trade for Nifty

There is a conception in market that there is a Santa Claus rally in December. For this month we are not even just 1.5% up till now and only 2 weeks are remaining.

I will try to quantify if there is any truth for Nifty about the Santa Claus Rally. Here are the few of questions I will try to answer the following questions:

1. Is there any Santa effect on Nifty?

2. When is the best time to buy for Santa rally?

3. What is the effect of yearly change on Dec returns?

Lets get the answer.

Santa Effect: Well there is a Santa effect on Nifty. But the time effect is not there in the December month.

The index has given +ive returns for 13 years for month of December in last 16 years. That’s a really good seasonal trade. The best here is average return for this month. It is 5%.

Now coming to timing the rally. Well it seems that there is no such trend for Nifty, while there is such a trend for western international indices. The international Indices do show seasonal +ive trend for 3rd week of December but such a trend is missing in India.

Though we cannot time the trade by weekly basis but if we buy at lows then this is the best trade. Now when to buy the lows.

Doing the past analysis it shows average lows of 3-4% from opening price for last16 years. But it is highly skewed data. The best buy point is about 2% low from the opening price.

Now lets see if there is any yearly change effect on Dec returns.

The trend shows that the more bullish a year is the more bullish December month is and vice versa is also true sometimes.

This year we are already 14% +ive for the year and December is now 1.5% +ive and the low was at -2%.

Conclusuion: The analysis shows that the index has been bullish during December month and the lows of about 2-3% can be bought for good upside returns.