Apr

26

No Uptick, from Kim Zussman

April 26, 2008 |

Knock knock!

Who's there?

Uptick.

Uptick who?

No Uptickrule 7/6/07

Some have suggested recent volatility may be linked to repeal of the uptick rule as of 7/6/07. Certainly volatility has been high since then, as shown by F-test comparing variance of post no-uptick with the prior period (at least in terms of SPY: stdev of cls-cls returns 93-7/5/07 vs 7/6/07-present):

Test for Equal Variances: post, pre1

95% Bonferroni confidence intervals for standard deviations

.     N     Lower    StDev     Upper
post   203 0.011560 0.012853 0.014457 (post-7/6/07)
pre1  3635 0.010327 0.010599 0.010885 (prior)

F-Test (normal distribution)

Test statistic = 1.47, p-value = 0.000

Levene's Test (any continuous distribution)

Test statistic = 18.53, p-value = 0.000

But in comparing the post-no-uptick period of 204 days to the 17 other non-overlapping 204 day periods since 2004, the recent period is not that unusual (see attachment: 1=post uptick, with 95CI for variances), and it would be hard to argue much beyond partial causation.


Comments

Name

Email

Website

Speak your mind

Archives

Resources & Links

Search