I wouldn't dream of going in front of a bunch of PhD's and baring a theory that lacked even a shred of mathematical rigor, such as the one I just posted. I was just offering what I thought was an interesting way of looking at the problem of runs, flawed as it was. :)
I think that psychology has more bearing on short-term stock movements than statistics.
Ah, but the two are inseparable. If statistics didn't indicate that stocks that move up can gather momentum and move up even more, people wouldn't pile on an obviously overvalued stock as it climbs. Likewise, statistics show that securities with large runups tend to face sizable pullbacks at some point .. which causes people to sell to keep their profits, which causes the price to fall and more people to sell, etc. This works at all granularities, both short and long term (stochastic processes such as stock prices can often be represented as fractals because of their frequent self-similarity). During heavy movement, stock prices stutter and head-fake, whether it's during a 3-minute, 3-day, 3-month, or 3-year interval.
Psychology and probability are Wall Street's chicken and egg. I think things happen the way they do because they have always done so, in one form or another ..
-G |
