Apr

10

107 Days, from Kim Zussman

April 10, 2011 |

It has been 107 trading days since QE2 was [officially] announced (Nov 4 2010). What has changed in the SP500?

SPY daily (cls-cls) returns were compared to zero for the 107 days since - and just before - the QE2 announcement:

One-Sample T: pre, post

Test of mu = 0 vs not = 0

Variable  N    Mean   StDev   SE Mean      95% CI            T      P
pre        107  0.0014  0.0109  0.0010  (-0.0006, 0.0035)  1.34  0.185
post      107  0.0008  0.0076  0.0007  (-0.0005, 0.0023)  1.21  0.230  

The pre-QE2 daily returns were actually slightly higher than since QE2: 0.14% vs 0.08%, with both not significantly different than zero. Despite civil war in the Middle East and the Japan earthquake, however, volatility post QE2 has been significantly tamed*:

Test for Equal Variances: pre, post

95% Bonferroni confidence intervals for standard deviations.

        N    Lower    StDev      Upper
 pre   107  0.0095  0.01097  0.01294
post  107  0.0066  0.00768  0.00907

F-Test (normal distribution)
Test statistic = 2.04, p-value = 0.000

Levene's Test (any continuous distribution)
Test statistic = 6.32, p-value = 0.013

*at what cost?

Alston Mabry comments: 

My comment immediately seems too terse, especially given that Dr Z endeavors perhaps more than anyone to add actual quantitative analysis to Spec List. The difference between announcement and implementation in this period modifies the old saw to, "Buy the rumor, then keep buying the news, but not so vigorously."

Bill Rafter writes:

My method for identifying character changes in a market is to take an indicator that you think reflects such character and then keep smoothing it and observe what happens. It does not matter that the indicator is leading, coincident or lagging, since for this exercise you are not in the forecasting business. At some point you will see certain parts of your manipulated data become very smooth while other parts retain some craziness. The chart below (previously posted) is an example. In this case the data is smooth before September 2010, but definitely more erratic from September 2010 onward.This data is a smoothed version of the difference in open interest between equity calls and puts. One might come to the opinion that despite the fact that the Fed does not dabble in equity options, they are nonetheless influenced by the Fed's presence in the marketplace. 


Comments

Name

Email

Website

Speak your mind

Archives

Resources & Links

Search