Skip to content

Analysis of Gaps and Holes

May 10, 2009

I have run some analysis on the occurrences of gaps in 50 share Indian benchmark index, NIFTY, with data from 2005 to April 29th 2009. Around 4 years worth data.

But before I start, two disclaimers:

  • The data on which I worked is not detrended hence it has a huge influence of the market we are in. Although, I have tried segregating the analyses as per the underlying market fundamental as well…(read my second disclosure as a continuation)
  • This is not a polished drawdown optimised trading idea. Its just an investigation. But if  you think you are filthy rich, and would love to trade it,be my guest[I wouldn’t mind sharing part of the profit though 😉 ]

Now, lets concentrate on the meat of this post, shall we?

Studies on the NIFTY price series from 2005 to 2009[around 4 years of data, coupled with 900-1000 odd data points], we had around 389 instances of gap downs, where today’s open was less than yesterday’s close.

Out of that we had 256 instances when the overnight gasp was filled. That is, at some point of the day, the high of the day was greater or equal to yesterdays close. Interestingly, a high percentage of the gaps were filled. An important thing we all should remember is that 2k5 to 2k8 were raging bull runs, and 2k8 to 2k9 were raging bears. Hence, I don’t know if this result is due to the upward bias in the dataset(or not). When I measured, the variation of the gap analysis with respect to the 15 day average volatility [15 day ATR], I got some interesting conclusions.

But before that, let me present to you some statistical numbers:

Study 1: Analysis of Overnight downward gaps [scaled percentage by volatility] that got filled

Mean Gap Down[PointWise]: -20.39 pts
Std. Deviation Gap Dn[Pointwise]:27.53pts

Mean Volatility Gap Down[Percent]: -18.75%
Standard Deviation [Pct]: 20.14%
Kurtosis: 3.37 [Leptokurtic]

The frequency of gap down[volatility pct scaled]graph looks like this:

Distribution of gaps which got filled, along the volatility axis

Distribution of gaps which got filled, along the volatility axis

To be continued…

Advertisements
No comments yet

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: