Counting the Carnage, from Jay Pasch
Measured yesterday's SPX closing price as a percentage decline of more than 4 standard deviations below the average one-day percentage change measured over the last 30 trading days. Examined the dates in history of like moves and the percentage-change T-days out. History shows a strong bounce averaging 4.3% by 2-days out, 9 of 10 winners and 1 no-change, t=3.2 at day-2.
Bernd Dittmann adds:
I continued Jay's counting, but instead of using confidence intervals, I looked at extreme values. Based on daily returns from Jan. 2, 1987 till today (4992 obs.), here are the left and right tails of the return distribution:
%return <-% obs normal >+% obs
0.1 2184 2321 2418
0.5 1466 1865 1663
1 876 1337 1041
2 334 596 371
3 140 182 136
4 69 50 61
5 36 9 27
6 23 1 15
7 18 0 9
8 12 0 5
9 8 0 2
10 6 0 2
What is clearly striking is that declines of 3% or more have been observed more frequently than 3%+ percent increases. If one were to use a normal distribution to describe Hang Seng daily returns (which is rejected at any level of significance), one would clearly underestimate the frequency of extreme returns. Which distribution would thus fit Hang Seng returns, and also its asymmetry in extreme values?
Larry Williams remarks:
Traders should carefully note which stocks in the Dow were the least resistant to the selling pressures yesterday. An important subject, raised by Victor and Laurel a few weeks back.