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 : Technical analysis for shorts & longs -- Ignore unavailable to you. Want to Upgrade?

To: Johnny Canuck who wrote (36610)	4/1/2002 4:03:45 AM
From: Lachesis Atropos	Respond to of 69370

Hi Harry re. Did you calculate the probabilities over all data points for each of the stocks? Yes. >> What happens when you use only the data points that only include moves of more than 7 percent? If I am reading you right then the time frame between the two tickers would get out of sync. Magnitude such as a percentage move is difficult to deal with. I am open suggestions! You are right noise is also difficult to deal with. The probabilities are not exact as I would like. I used a 7 day moving average as a filter. I fiddled with 2 to 25 day MA's and concluded that a 7 day MA gave the best results. I think this could be further refined. I would guess that the volatility of each ticker could be used as a parameter to increase or decrease the MA for the ticker under analysis. One would still need to eye ball the results. As it is, the page calculates a 7 day MA for each ticker, then it compares the MA's by direction (disregarding magnitude) over a time period of Jan 1 2001 to March 28 2002. If both 7 day MAs are moving in the same direction on the same day a count is incremented. I get the probability by dividing the count by the number of trading (308) days in the time period. If you or anyone else has any ideas let me know. Lawrence