Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Strategies & Market Trends : MDA - Market Direction Analysis -- Ignore unavailable to you. Want to Upgrade?

To: ru2 who wrote (61702)	11/1/2000 3:24:44 AM
From: jttmab	Read Replies (2) \| Respond to of 99985

Amazing how someone [ahhaha] can gander so much disagreement and dislike over such a short period of time, yet acquire so many posts... In an attempt to be a little constructive towards his "argument". The coin toss was a poor model of choice. It might have been a better gaming model to select....blackjack. The outcome of a hand of blackjack is somewhat random since the order of the cards is random. The population of the cards and the rules make it waited in favor of the house. One has [basically] three outcomes in each hand played: win, lose and draw. To carry the analogy a little further, card counting could be excluded as a strategy, by assuming the market is a multi-deck blackjack game with an infinite number of decks. The construction of the graph, an x-y plot, x would represent time, or each successive hand played. To simulate a days trading, one could collect a set of successive results, e.g., x sub n through x sub [n+1,000,000,000] and plot them in the same relative point on the x-axis. The next value would be x sub n+1,000,000,001 through x sub n+2,000,000,000 and so on. The y value might be viewed as the value of the NAZ [the house] adjusted by each tick [hand of balckjack with a .01 unit bet]. Since each result is "random" but weighted towards the house, over time the value of the NAZ would be expected to go up. Yet given that random strings of wins or losses can occur over the short term, the NAZ would go up or down over the short term. There would be a much larger number of hands by orders of magnitude, than 10,000 to plot a chart over a lenghty period of time. [Even orders of magnitude larger to plot one day's activity.] One could further complicate the model by varying the number of hands played during a day, simulating daily volume. Clearly, the model needs a lot more refinement, but that's the gist of it. When you're caught up on all your business related actions, household chores, reading, vacation, shopping, washing your hair or car, etc., it would be an excellent activity to generate such a chart from the model.<s> Alternatively, one could apply for a Federal grant to do such a study in support of the determination of whether to add social security funds/revenues to the market. Best Regards, jttmab

To: ru2 who wrote (61702)	11/1/2000 6:00:03 AM
From: HairBall	Read Replies (1) \| Respond to of 99985

ru2 and all: I asked ahhaha to drop the insults and off topic conversation, he complied...please do the same. Regards, LG

To: ru2 who wrote (61702)	11/1/2000 6:30:55 PM
From: RocketMan	Read Replies (2) \| Respond to of 99985

At the risk of revisiting the recent diatribes going back and forth on random walks and the market, I would like to add an observation, fwiw. Ahhaha is right about the market fitting a random walk model, that is, a first order markov process in discrete time (weiner process in continuous time, if you believe such a thing is possible). This is neither a new nor a particularly interesting statement. A number of theoreticians have reached this conclusion, and it is even used as an example in the Box-Jenkins time series textbook. However, ahhaha is wrong about one important thing -- it is not the periodic market values that are best modeled by a random walk, but the residuals -- the error terms. That is also not surprising, since the residuals are the sum total of all of the buys and sells during the day, which represent the market's efficiency, and collective ignorance. What is more significant is the long term trend, which is not best fit by a random walk, at least not in the time frames of interest. Going back for at least a century or more, the trend has been positive, with certain cycles that many have tried to decipher. This does not help the short term trader, that is, anyone with a time frame shorter than a year or so, but it is a clear enough trend that one can conclude statistically that a pure random walk model can be rejected in favor of some type of markov process with a trend (e.g., an arima model in time series terms). I would have contributed to this discussion earlier, but chose to sit on the sideline, having been accused of being a lemon sucker or something equivalent to that in previous discussions on the matter -- I only have a doctorate in stochastic processes, and am not the only expert in the world who is qualified to speak on such heady topics -g-