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 : Stock Attack -- A Complete Analysis -- Ignore unavailable to you. Want to Upgrade?

To: James Strauss who wrote (27969)	8/19/2000 1:31:46 PM
From: donald sew	Respond to of 42787

James, As I have mentioned before and for those who are familiar with statistical analysis, to be considered statistically viable the rule of thumb is 32 repeated patterns. That doesnt mean that a pattern which is less than 32 times cant work, just that mathematically it is not commonly considered statistically viable. I can give you 1:1 comparisions that worked, but they are still not statistically viable. Would I totally ignore a pattern that repeated less than 32 times, of course not - I would keep it in somewhere in my brain. Keep in mind that by using only 10 years of data, such would be only during the bull run, so that would ignore what happens in bearish markets. How did that pattern work in the 70's or 80's, when things werent so bullish. I dont know, just asking a question. So if one limits the set to only the last 10 years, which were bullish then one is also making the assumption that the performance of that pattern during a bearish period should be disgarded. That approach could work out the way you want and it may not, but its not statistically viable. I dont know how it did, just stating a point. The same goes with overly bearish views where many compared todays market to 1929. Thats not statistically viable either. I will mainly stick to statistically viable issues and sometimes I will be wrong. As for probabilty based on statistics, my view is that the big call(whether in terms of price movement or time) has no better than a 62% probability of predicting it correctly at best. seeya