Probability - or, when is it better to stay in bed?

[BeginnerJoe]

If you are so sure you will lose after 7 winners, then I suggest you get up extra early and do a reverse trade on the 8th. Then you will get 8 winning trades in a row. No doubt you will then be hit with the dilemma of what to do with the 9th trade, since it surely must be even more impossible to win 9 times in a row. Perhaps, after so many winning trades, you will retire and forget about the whole thing.

 

[robster970]

Doesn't a random distribution of wins and loses predicate that each event should be seen as discrete or is that too simplistic?

 

[barryb]

sorry martingoul but i think a binomial is more appropriate but in this simple case they are sort of the same but not acutally the same.

but I say binomial is better because 0.5 < p < 0.95. i also think binomial is more appropriate just from experience



but anyway yes the second bit is very interesting like autocorrelation in results and stuff like that

Gay intellectual masturbator.

 

[Chartsy]

so basically; probability of winning X times in a row is the probability times the winning percent to the power of the number of consecutive wins.

Whereas, the probability of winning is just the winning percent always?

eh that's another point; if you have a win rate of 50% based of a sample of trades, what if you lose so many trades it affects the win %- is that considered a drawdown? surely your win% is always changing!

 

[DashRiprock]

Gay intellectual masturbator.

fancy a reacharound?

 

[Jason101]

The chances of a win are exactly the same on each trade, if your entry set ups are the same.

The amount of wins in a row is a very separate question and is purely retrospective, therefore it should not influence your current or future actions.

 

[DashRiprock]

so basically; probability of winning X times in a row is the probability times the winning percent to the power of the number of consecutive wins.

Whereas, the probability of winning is just the winning percent always?

there are 2 basic points here

1) "if you toss a coin after 7 times on a head, you shouldnt bet on a head for the next time". Just look up conditional probability, the Probability"8 heads in a row" | Youve already got 7 heads in a row) == Probability(result is a "head")

the second, more interesting one is

2) are market conditions homogenous? Are there feedback loops? Is it appropriate to extrapolate past conditions into the future?

 

[tomorton]

do u actually think this is true?

I rekon ur just doing this thread for LULZ

No Dash, this is the problem I face every week, we all do, it's just more stark for me as I do 1 trade only per day.

This debate arises from a real scenario with real money. In May, by the 20th, I was ahead 10 trades to 2 (each trade having the same £ target and risk). To go 8 trades up in any 3 week period is unusually good performance for the system, so I considered ceasing trading until a few more losers had restored performance to more like the mean. Instead, I decided to continue trading as normal (as every trade is 60% likely to be a winner!) and subsequently made 1-5 in the rest of the month, ending May at 11-7. This is not bad, and is very close to the long-term 60% win rate but by trading through, I halved my month's profits in the last 6 trades of May.

As far as I can tell, there is no reason why any result from the system on a day should influence the outcome of the next.

I feel definitely outnumbered here but not only is my argument intuitively correct, but I have system performance in May as an example to back me up - everyone else, with the respect due to co-workers, just has theory.

 

[Jason101]

there are 2 basic points here

1) "if you toss a coin after 7 times on a head, you shouldnt bet on a head for the next time". Just look up conditional probability, the Probability"8 heads in a row" | Youve already got 7 heads in a row) == Probability(result is a "head")
the second, more interesting one is

2) are market conditions homogenous? Are there feedback loops? Is it appropriate to extrapolate past conditions into the future?

Not true at all. The chances are still 50/50.
You are confusing 2 questions. If you were to ask what are the chances of getting 8 heads in row then you would be correct. The trick is regarding what is the original question and your original aim to set out to prove.

 

[DashRiprock]

Not true at all. The chances are still 50/50.
You are confusing 2 questions. If you were to ask what are the chances of getting 8 heads in row then you would be correct. The trick is regarding what is the original question and your original aim to set out to prove.

I think you misunderstood my answer. The bit in quotes "if you toss a coin after 7 times on a head, you shouldnt bet on a head for the next time" is a paraphrase of the OP, and wrong.

Like you - and i - said, the probability is whatever the probability of the original event is*

P(8 heads | 7 heads) == P(1 head)

* this is the interesting 2nd point, is it or isnt it?

 

[Jason101]

Dash,

My fault, (toggling to supermarket order whenever the wife comes near).
Yes we do agree.

Your second point could either be very deep and surreal or the trader is un-wittingly negatively correlating his markets or trades.

Or
Maybe his trades do not suit the end of the week.

Or
Maybe it is a psychological issue for him.

 

[DashRiprock]

* you can never know what the probability of your next trade is, you can only guess
* the market is not always the same
* Heisenburg principal
* feedback loops

 

[amit1986]

Trading really is a probability business, but those with a strong edge know how to overcome the odds.

If I've had a good run of three or four successful trades in a row, then I definitely take more serious note of any upcoming trade, as it increases the likelihood of the next trade being a loser.

 

[DashRiprock]

lol

when I am doin good I trade bigger
when I am doin bad i trade smaller

 

[tomorton]

amit has summed it up - although the market behaves in each session as it always does, the way we interact with it in order to extract profit should be affected by the preceding sessions. I say stay out, amit says be extra attentive, but we both accept the principle.

 

[amit1986]

lol

when I am doin good I trade bigger
when I am doin bad i trade smaller

sweet and simple LOL

 

[Masquerade]

Well I have to say that this thread's really been insightful in weeding out those who people shouldn't take advice from.

Thank you.

 

[BeginnerJoe]

Well I have to say that this thread's really been insightful in weeding out those who people shouldn't take advice from.

Thank you.

I am still scratching my head. So, which ones we shouldn't take advise from ? Given that psychology and emotions (suppression of which) are huge components of trading, it's probably better for people to believe what they want to believe in order to have a peaceful mind that they could actually use for trading. If someone doesn't feel comfortable after an X number of wins, then it's better if they didn't trade after that. Otherwise the discomfort will interfere with the trade decision turning the fear into a self fulfilling prophecy.

 

[Jason101]

Well I have to say that this thread's really been insightful in weeding out those who people shouldn't take advice from.

Thank you.

Are you not going to show your cards then?

 

[Masquerade]

Are you not going to show your cards then?

I only show them when i'm all in.

What's there to show, this is painfully obvious probability and concepts that i'm baffled people need it spelt out and still don't get it. I support pretty much everything Hoodoo Man has said in this thread. Pay attention to what he says.