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

[EmotionIsTheBigEvel]

lol

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

It's a quote from Paul Rotter...who made to much money...

The problem with this quote according to Paul is that it is against Human natur, after a losing trade you would love to play bigger to make up for your losing trade, while after a good trade you would like to play smaller because you are afraid to loose it all on your next trade...

 

[Jason101]

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.

I think you must have crossed threads, as far as I am aware Hoodoo Man has not posted in this thread.

I cannot understand why people talk in riddles. As far as I am concerned it is basic school boy maths every new trade has an equal chance of success, simple no question.

I cannot understand why anyone would think anything differently and I cannot understand why anyone would not state their views simply, once they have decided to comment on the topic/thread.

 

[megamuel]

This thread is quite apt for me as a couple of weeks ago I started live trading a new EA I designed. Just on a small £350 account as it is more forward testing for now but so far it's had 10 trades and all 10 have won. So my advice would be, if you've had 7 winners in a row, KEEP TRADING!!! I'm also using 1:1 risk reward with this EA so I'm sure there is a bit of beginners luck there but I'm ok with that. In fact, a run of 10 winners beats the maximum consecutive winners in a 3 year backtest so definitely beginners luck! I'm still going to trade it tomorrow though.... In fact, I'm feeling luck! ;-)

Sam.

 

[besttraderalive]

The issue is the math your using is conplacent with overall trade history. What people are try to get you to see is this. A system with a given % win rate means that for every signal your system gives so much % of the time for its history of use you will win. Thus at best the market only does 1of 2 things go up or down which is 50/50 for any given trade. So a stoploss is the best way to keep money in your pocket..

 

[TheBramble]

Bernoulli dist with 2 discrete results IS a binomial distribution.

a Bernoulli becomes a poisson when you do it in continuous time


(iirc)

And he swishes his red cape with an artful half twirl to the left being passed within the merest fraction of an inch by the horns, of the goat.

 

[TheBramble]

Is the logical conclusion therefore with this system to stay out of the market on any day following two consecutive winners?

No. That wasn’t the logical conclusion. Some really good advice given by some, but in essence, you don’t know how long your string of winners or losers is going to be. You might want to take a stab at calculating the probabilities of each given the performance data of your system, but it’s all quite pointless.

If you’ve got a 60% winning setup AND you’ve got positive expectancy, just keep swinging and use spare intellectual capacity improving the basis for your setup, win rate and expectancy, or other useful exercises like posting on this site.

One member suggest increasing your stake on good runs and decreasing it on bad ‘uns. Doesn’t work for me as I’ve always managed to undo all the good stuff in those last couple of trades on the end of the good run and hit the two good un’s on the end of the bad run with pitiful and pointless size. But maybe that’s just my experience.

 

[DashRiprock]

bramble I think it was me who said about trading more size when doing well, but i dint really mean "stake size"...

... for me, I have 2 strategies. One is just working around the order flow trying to catch a few ticks, like being long when someone is doing alot of accumulating and letting the shorts puking take me out. The second is that I have one or 2 hypothesis of what days action will be like. If I am up a good amount from the first way, I let myself risk some of my account on my hypothesis if it comes about.

So say like my hypothesis is "pain trade to X then rally to Y", and when it gets to X I am up a good amount, I keep some contracts in the bag and carry on scalping with a long bias.

 

[TheBramble]

Well yes, it was you Dash, but I didn’t want to inflate your ego further by letting you know I read your post with interest.

So if you’ve made a ‘goodly amount’ on your bread and butter order flow plays (presumably that equates to you being up more than your target for that point in the day?) and you’ve got some play money, you allow yourself to take a punt with capital you have accumulated over and above target, which you don’t mind too much if you lose?

 

[DashRiprock]

not necessarily a fixed dollar target, there is a bit of discretion in there too. and I dont automatically punt it either, it has to be shaping up nicely. I don't like to risk being down on the day if my hypothesis is wrong tho.

like when im doin badly, I dont have a fixed target like # of good trades or % appreciation from equity low to go back to normal size, I just wait until i get my mojo back.

 

[TheBramble]

Didn’t mean ‘punt’ pejoratively mate, I appreciate you probably wouldn’t take a position unless you felt you had a better than average chance of getting out on top.

As for getting your mojo back (and realising you’ve lost it in the first place), that suggests far more sensitivity and situational awareness than your average trader, pro or retail, is ever likely to get the chance to develop.

Have you been in touch with the woman inside, have you Dash?

 

[DashRiprock]

I bash my mojo out regularly

 

[forker]

i have a question, how many trades must you get wrong before you think its lack of mojo?

 

[DashRiprock]

flat / down over a 5 or 6 week period depending on trade frequency. If I'm askin, I'm usually dancin'.

 

[TheBramble]

Weeks!

FMG!!!

You need a big German bitch in tight leather with a whip standing over you son.

5 or 6 minutes without a winner and you feel the lash....

 

[forker]

or perhaps she is wearing a strapon

 

[TheBramble]

Well, if she uses the strap-on 60% of the time and the whip 40% of the time and my bottom still hurts, what's the probability that....

 

[Masquerade]

I think you must have crossed threads, as far as I am aware Hoodoo Man has not posted in this thread.

I cannot understand why people talk in riddles. As far as I am concerned it is basic school boy maths every new trade has an equal chance of success, simple no question.

I cannot understand why anyone would think anything differently and I cannot understand why anyone would not state their views simply, once they have decided to comment on the topic/thread.

Yes, it'd appear I did. It was fairly similar to this one. Either way, go check out his stuff - it's good.

Every new trade has an equal chance of success IF each event is independent. Now the question is: do you consider each trading day to be completely independent events or is there a relationship between trading days?

 

[Martinghoul]

There's no way to know... Moreover, you can't make an easily justifiable assumption about independence. That's why the problem becomes interestingly complicated.

 

[the hare]

There's no way to know... Moreover, you can't make an easily justifiable assumption about independence. That's why the problem becomes interestingly complicated.

Intuitively, it seams resonable to assume that if you where trading something like a trend re entry system, taking multiple small bites out of a longer term trend then you'd see some degree of serial correlation. In practice, I certainly havnt been able to measure this, and people with way more experience than I claim that trades are independant.

Presumably, the statistical methods that are commonly used to measure this are inappropriate (or maybe the way we pre process the data). It always worries me when something that seams intuitive isnt bourne out by statistics.

 

[tomorton]

Most people are saying every trade is an independent event so trade it as a unique trade, regardless of previous results. I am quite severely chastised for poor maths.

However, some of the same people are lately saying, that actually they amend their trade management rules depending on their success / failure. I don't think you can have it both ways.