Poll: Are you statistically superstitious?

[Avalanche]

Quote from WDGann:

Each trade is independent.

. //period

That is crazy. His system isn't likely to simulate spinning a rolette wheel or random entry. It is going to have a bias in which it wins more either with trending conditions or during chop, or some other bias.

Thunderdog's thinking was logical IMO, your response on the other hand to call him a bunghole? What are you a 4th grader? He did nothing to garner an insult.

 

[WDGann]

I'm a 3rd grader.

Does each individual trade reflect the statistics? NO

For example...

Consecutive Win/Loss is a historical characteristic under a set data. Each and one individual trade doesn't reflect in itself. Cumulative Analysis of trade"S" are the statistics.

Simple explanation, bunghole"s" get it?

 

[hypostomus]

...I think I get the essential disagreement here. You think trades are independent because it's a complex free market. I think they aren't because it's MANIPULATED. How does manipulation fit into your world view, espece de con? Best regards. - Mike

 

[profitseer]

Quote from hypostomus:

Rigid mechanical system traders: Up to this morning I had six straight wins, one more than the longest streak in my backtesting. The system triggered a trade this morning. Would you take it, fade it, or stand aside?

I must be missing something complicated. If you're a system trader, you just go back and check longest streak, or check how many 6 streaks went on to become 7 streaks and ho many were broken on the next trade, or performance figures for the next 6 trades after a 6 streak win. You can test it up one side and down the other if you are a backtester.

What if you find after every 6 streak 73% of the next 3 hits 2 out of 3? Then you got it made. 1 unit on the next trade, if it's a loser then blow the wad and let it ride on the next two!

(dry powder is for discretionary traders to sit on)
system traders already have something else crammed up there

 

[hypostomus]

...thanks for that suggestion. Never thought of it that way, was thinking interms of the longest winning and losing streaks, and how long the stresks following them typically were.

 

[PetaDollar]

Whether the trades are independent or dependent depends on the method and the time scale. Anyway, it's easy enough to calculate the probability of a win, following a win, vs. following a loss, and answer your own question...

Ever heard of adding to your position if the trade goes the right way? There area plenty of studies that show trend following systems benefit from adding to your position. If the trades were independent that wouldn't be the case, for this system.

Better yet, if signal A ends up working, what's the probability the next signal B will work, as opposed to the probability of all signal B's?

One thing I found was the famous three bar pivot breakout method (signal B) has a significantly greater probability of success on a gap day (signal A). This was on the entire March 03 NQ contract.

Statistically independent trades means there is no "bigger picture" to view the method against. Put another way, things we don't understand appear random.