Jan
27
Quite a Scan, from Victor Niederhoffer
January 27, 2012 |
Since December 19 2011, we've gone through a remarkable bullish period in the market. We had 19 out of 23 days up as of close yesterday. A good way to quantify these is with scans, a variant of runs except instead of x in a row in the same direction, it's x out of the recent y in the same direction. Like runs, scans could be quantified with magnitudes by multiplying the consecutive changes adjusted for mean together and normalizing by a goodmanesque number.
One notes that out of the last 3400 daily trading days from year end 1995 in S&P, such an event occurred just 5 times; all such happened in 2010, around the middle of March, March 12, March 16, March 22, March 23, and Nov 9 (note the failure of independence and thus the need for a real goodmanesque adjustment). One notes that 20 days later they all were up, an average of 3%. Rocky Humbert rules again.
It is interesting to note that there has never been a 19 or 23 down, but there were four, 17 of 23 down, all around Aug 8th, Aug 10, Aug 22, and one outlier 9/29/1999. Anyone who didn't take out the cane during those times, lost a quick 6%. It is interesting to reflect on this phenomenon and to see the "expert " for what he is.
A nice application of scan statistics is contained in Fast Spatial Scan .
A textbook on scans from Wiley is Balakrishnan, N. and Koutras, M. V. (2002): Runs and Scans with Applications.
Also, one notes that bonds have set some nice clusters, with 19 of 23 up occurring 3 times since 1996 being bullish.
Comments
2 Comments so far
Archives
- May 2013
- April 2013
- March 2013
- February 2013
- January 2013
- December 2012
- November 2012
- October 2012
- September 2012
- August 2012
- July 2012
- June 2012
- May 2012
- April 2012
- March 2012
- February 2012
- January 2012
- December 2011
- November 2011
- October 2011
- September 2011
- August 2011
- July 2011
- June 2011
- May 2011
- April 2011
- March 2011
- February 2011
- January 2011
- December 2010
- November 2010
- October 2010
- September 2010
- August 2010
- July 2010
- June 2010
- May 2010
- April 2010
- March 2010
- February 2010
- January 2010
- December 2009
- November 2009
- October 2009
- September 2009
- August 2009
- July 2009
- June 2009
- May 2009
- April 2009
- March 2009
- February 2009
- January 2009
- December 2008
- November 2008
- October 2008
- September 2008
- August 2008
- July 2008
- June 2008
- May 2008
- April 2008
- March 2008
- February 2008
- January 2008
- December 2007
- November 2007
- October 2007
- September 2007
- August 2007
- July 2007
- June 2007
- May 2007
- April 2007
- March 2007
- February 2007
- January 2007
- December 2006
- November 2006
- October 2006
- September 2006
- August 2006
- Older Archives
Resources & Links
- The Letters Prize
- Pre-2007 Victor Niederhoffer Posts
- Vic’s NYC Junto
- Reading List
- Programming in 60 Seconds
- The Objectivist Center
- Foundation for Economic Education
- Tigerchess
- Dick Sears' G.T. Index
- Pre-2007 Daily Speculations
- Laurel & Vics' Worldly Investor Articles
It seems like nothing can possibly go wrong in the markets? Every possible contingnecy has been talked about and even a Greece default is now seen as a positive.
Every dip seems to be bought-it appears that nothing can really cause much turmoil and the vix is very calm.
Something a little off on the math if I’m reading the above properly.
I’m using the SPX Index as the market.
From 12/19/11 through 1/27/12 is 26 trading days. There are
19 positive days in that time. If I run a simple average on
my Excel sheet, 19/26 = 73.07% positive.
Looking back to 1995 with a 26 day moving average I find
27 times the average exceeds 73% or 19 positive days in 26.
Looking at the +5, +10 & +20 day returns on those dates gives me an average of -1.2%, -2.2%, -3.3% on those events and time frames.
On the 5 day, 37% positive, 10 day 30% positive, 20 day 22% positive.
Am I looking at the concept of scans wrong?
The best runs were 1/19/10, 1/15/10, & 1/14/10 with 20 positive
days over the 26. Those three events had some of the worst returns.
% positive days 5 day 10 day 20 day
2/28/11 73% -1.3% -2.3% -1.3%
2/22/11 73% -0.7% 0.5% -1.6%
2/18/11 73% -1.2% -2.4% -3.3%
2/17/11 73% -1.5% -1.4% -4.6%
2/16/11 73% -2.3% -0.4% -4.7%
1/6/11 73% 0.8% 0.7% 2.9%
1/5/11 73% 0.7% 0.3% 2.4%
11/5/10 73% -2.2% -2.1% -0.2%
5/3/10 73% -3.5% -5.4% -10.9%
4/20/10 73% -1.9% -2.8% -7.2%
4/15/10 73% -0.2% -0.4% -4.5%
4/14/10 73% -0.4% -1.6% -3.2%
4/6/10 73% 0.7% 1.5% -1.3%
4/5/10 73% 0.8% 0.8% 1.2%
3/23/10 73% -0.1% 0.7% 2.7%
3/17/10 73% 0.1% 0.3% 3.9%
1/20/10 73% -3.6% -3.6% -2.7%
1/19/10 77% -5.0% -4.1% -4.4%
1/15/10 77% -3.5% -4.1% -3.6%
1/14/10 77% -4.9% -6.5% -6.4%
1/13/10 73% -2.5% -5.3% -5.9%
1/12/10 73% 0.2% -3.4% -6.0%
1/11/10 73% 0.3% -4.8% -6.7%
1/8/10 73% -0.8% -4.2% -7.7%
1/7/10 73% 0.6% -4.4% -6.6%
1/6/10 73% 0.8% -1.8% -6.5%
4/20/07 73% 0.7% 1.4% 2.6%
Avg Return -1.2% -2.2% -3.3%
Std Dev 1.8% 2.4% 3.9%
# positive 10 8 6
% Positive 37.0% 29.6% 22.2%