(binned per thread starter's request) The Monty Hall Problem appl | Page 2 | Forex Factory

Options

Go to
Permalinks
Print Thread

Similar Threads

Forex Factory Hall Of Fame 126 replies

Monty python and the holy grail 4 replies

Programming Request: Hall of Fame 5 replies

Attachments: (binned per thread starter's request) The Monty Hall Problem appl
Exit Attachments

(binned per thread starter's request) The Monty Hall Problem appl

  • #21
  • May 26, 2017 4:32am May 26, 2017 4:32am
Quoting Mingary
.... 1437 lines of code, I really need a break now ...
Here's your lucky break .... use table-driven logic, it allows you to think about the problem without being swamped by the code.
Or perhaps a state-machine, but if this is meaningless to you I suggest using this (http://www.cammegh.com/product.php?currprod=pitboss).

Quoting Pips_Cruiser
It appears to have elements in common with this strategy: https://www.forexfactory.com/showthread.php?t=405
From which perhaps the most useful extraction is this....
Quoting marejp
If you don't put the MACD and RSI on your chart the brokers will never know where the high or low for the day are suppose to be on their charts
Carbon-Dioxide: the gas of life! https://youtu.be/ttJBdr6eBuo
  • #22
  • May 26, 2017 12:28pm May 26, 2017 12:28pm
It would be a little TOO ironic if Mingary discovered and shared something like that.

Of course, he might be a snake oil salesman.

http://www.npr.org/sections/codeswitch/2013/08/26/215761377/a-history-of-snake-oil-salesmen

Attached Image


But it's even more likely he's "pulling our leg".

https://www.youtube.com/watch?v=cZUrk9tjnZY
  • #23
  • May 27, 2017 7:11am May 27, 2017 7:11am
Quoting Mingary
1) the price-time series is random 2) entries react to price discovery (opening a door) The code makes position adjustment according to price discovery (i.e. opening a door) {image} The idea is to navigate through the random price series while keeping a positive account balance.

Can someone Kindly explain what that means
  • #24
  • May 27, 2017 7:30am May 27, 2017 7:30am
Quoting Pips_Cruiser
It would be a little TOO ironic if Mingary discovered and shared something like that. Of course, he might be a snake oil salesman. http://www.npr.org/sections/codeswitch/2013/08/26/215761377/a-history-of-snake-oil-salesmen {image}
After I got into minute level scalping game and researching it intensively I sure got a taste of all of that crap in the snake oil poster. I've figured out it has all to do with peripheral circulation constriction (caused by stress) and then when it's constricted and you sit around all day, the flow rate (or some similar parameter) of blood is such that all sort of minerals, hormones and whatever can build up (atherosclerosis). This doesn't seem like a problem theoretically but since the circulation is a tree like structure in a way, the smallest veins and such don't expand enough so once they get jammed up from the peristent low flow condition you get stuff like those symptoms and "bad fat" build up - the kind that body won't consume as it's more like junk food and whatever pill ingredients you've been popping while hoping to fix the stress condition.

After it got quite nasty I found that just walking and exercise may not be quite enough to give relief so then you end up trying yoga and massages etc which help more but I'm also researching solutions that would unclog the atherosclerosis build up but there's still the problem that even if you do take some pill, getting the unclogging ingredients all over the body doesn't quite work so simply. So you really need to do exercises + massage and lots of relaxation and no stress and possibly the pills too (same day you're doing all that) to get relief from all that symptoms listed. I would guess good portion of mental health problems are related to this and another portion is related to expectations and or lack of meaning and such things. I've come across some studies suggesting that taking a bunch of pills causes build up in kidneys etc of things they can't quite handle (all sort of pharma pills tend to be quite intense dosages, it's preferable to chop them and take in small amount over the day with food and drink if you really feel need to take any pills imo - I started taking some vitamins because of sleepyness/brain fog and it was really more to do with diet and the toxic fumes from my hobby of spending money on cheap chinese electronics. Throwing smelly materials such cables outside and buying air conditioning and eating less bakery products helped quite a bit with the brain fog and tiredness. I've also read research that chemical cleaning agents common in grocery stores can be very dangerous in ways that are not mentioned in disclaimers. Mineral-void water and wet+dry rag is superior because those chem agents leave residual traces that end up in the lungs and then your oxygen intake goes worse. Sub 40% RHumidity is also problematic as air pollutants start to irritate lungs more at low humidity).
  • #25
  • May 27, 2017 8:12am May 27, 2017 8:12am
if its random data series then u should get different results for duplicated back tests
WaBaS Where are Buyers and Sellers
  • #26
  • May 28, 2017 1:16am May 28, 2017 1:16am
Quoting dagoods
{quote} Can someone Kindly explain what that means
1) Let's say that the goal is to either keep the balance at break even or increase the balance. Therefore, a drop in the account balance is not allowed.
2) Place a random trade (time zero; t0) in the random price series (price zero; p0)
As the price series develop (p+n); What happens to you entry at t+n ?
What needs to occur so that 1) is never violated ?

Some sort of Martingale scheme may be the obvious answer, but invariably they always crash ...
  • #27
  • May 28, 2017 2:01am May 28, 2017 2:01am
Quoting mr.brown
if its random data series then u should get different results for duplicated back tests
Agreed. If you entries are truly random then every backtest should yield different results. One might be good. The rest garbage. But which one?

conclusion:
You don't need to apply Monty Hall to trading to be profitable.
You came here for the truth and let me unveil it for you
  • #28
  • May 28, 2017 2:43am May 28, 2017 2:43am
One could try to backtest by opening buy and sell nedge at each time point, and then managing the trades using this methodology. That way the question about different backtest results using a different random generator seed would be solved.
k
  • #29
  • Edited 7:00am May 28, 2017 6:45am | Edited 7:00am
Quoting RondaRousey
{quote} Agreed. If you entries are truly random then every backtest should yield different results. One might be good. The rest garbage. But which one? conclusion: You don't need to apply Monty Hall to trading to be profitable.

random or not... Monty Hall logic dictates, mandates, a fixed logical % win rate of 2/3 by switching doors once 1/3 of the answer is revealed as the wrong door.. The "backtest" of the monty hall game yields the same result every single time, without fail. So I'm not convinced that if you were actually running monty hall, that your back test would yield different results.
  • #30
  • Edited 11:54am May 28, 2017 6:53am | Edited 11:54am
Quoting Mingary
{quote} 1) Let's say that the goal is to either keep the balance at break even or increase the balance. Therefore, a drop in the account balance is not allowed. 2) Place a random trade (time zero; t0) in the random price series (price zero; p0) As the price series develop (p+n); What happens to you entry at t+n ? What needs to occur so that 1) is never violated ? Some sort of Martingale scheme may be the obvious answer, but invariably they always crash ...

huh?

what is it that is likened to opening a door? taking a trade? switching from long to short or short to long after a stop loss? martingale doubles after a loss and switches from long to short or vice versa... that is not like opening a door(revealing 1/3 of the wrong answer and a valid reason to switch) in my mind? so what is likened to opening a door(revealing what not correct to do AND why/when to switch doors and increasing ones odds to win/choose correctly)?

lets try this: lets start from the begining ..describe simply what happens: you take a trade...does that trade have a stop loss? does it have a tp? ok. if so there are 2 possible outcomes.... then what?


please be specific about how you liken that to monty halls opening of doors?

please be as exact as you can

TY
  • #31
  • Edited 4:52pm May 28, 2017 11:15am | Edited 4:52pm
Quoting emmanuel7788
Not 100% sure but I think I am on track with Monty Hall switch door before NY open. {image}
Attached Image (click to enlarge)
Click to Enlarge Name: Tester.jpg Size: 187 KB

Am I doing it right? wonder how much is your volume increase on opening new positions and how much floating DD was in risk ?
and about your dynamic stop loss, how Dynamic is it? Im using 2.5x ATR from the FIRST position, and not changing the SL on opening new positions. its also from the first position not from 10EMA, can you give more information about how are you doing it?

Thanks!


edit: this is fun while you know the "trend direction": (10 days trend example \/)
Attached Image (click to enlarge)
Click to Enlarge Name: Tester_2.jpg Size: 192 KB

what when it reverses? the "safety valve release" would be activated? but then you need to decide how much deep can you opening doors, because if the safety os too near, it would be activated to often, if too distant you would give much more when activated. this is the real problem I belive, decide the size of your safety release.
  • #32
  • May 28, 2017 11:49am May 28, 2017 11:49am
Quoting Mingary
{quote} 1) Let's say that the goal is to either keep the balance at break even or increase the balance. Therefore, a drop in the account balance is not allowed. 2) Place a random trade (time zero; t0) in the random price series (price zero; p0) As the price series develop (p+n); What happens to you entry at t+n ? What needs to occur so that 1) is never violated ? Some sort of Martingale scheme may be the obvious answer, but invariably they always crash ...

ok lemme try again...

1. i presume you do not use SL or TP ...is that correct? or at least until certain criteria are met, save perhaps an emergency stop loss order)...no?

2. at t+n the entry is in drawdown let's say.....so now what...you take a second trade,.....lets call it T2, after T1 goes negative? sounds like you need to whammy a little until the account goes positive... and then move the entire thing(all positions to an aggregate break even SL)when the account goes into a certain % positive equity... its hazy brother...can you spell out more exactly so us non-coders can understand...
  • #33
  • May 30, 2017 2:57pm May 30, 2017 2:57pm
Quoting mokuro89
{quote} {image} Am I doing it right? wonder how much is your volume increase on opening new positions and how much floating DD was in risk ? and about your dynamic stop loss, how Dynamic is it? Im using 2.5x ATR from the FIRST position, and not changing the SL on opening new positions. its also from the first position not from 10EMA, can you give more information about how are you doing it? Thanks! edit: this is fun while you know the "trend direction": (10 days trend example \/) {image} what when it reverses? the "safety valve release"...

run your new monster in live market for 1 ~ 2 years and you will learn a lot more because the market will teach you how to tame the monster.
Honesty is a very expensive gift. You wont find it in cheap people.WBuffett
  • #34
  • Edited 5:49pm Jun 5, 2017 5:22pm | Edited 5:49pm
Quoting Horne
"The Monty Hall Problem" only has a statistical advantage because Monty Hall knows where the prize is. He has to open a door that dosen't have the prize behind it - before offering you the opportunity to stay or switch. You're using Monty Halls knowledge of where the prize is to your advantage.

yes. exactly..... if we know what the price won't do... it's like knowing what is NOT behind door number 2.....

for example lets take three doors and make them analogous to three possible outcomes for each hour of trading EU

door number 1: price ranges and neither gains 20 pips to the upside nor does it decline 20 pips or more to the downside

door number2: Price gains 20 pips to the upside

door number 3: Price declines (goes short) 20 pips to the downside


so, now we need a "Monty Hall" to open a door for us and tell us what price is NOT going to do..... Lets make taking a 1 hour demo trade analogous to having Monty Hall opening door for us..... the demo trade opens the door slowly...... and then boom it does one of the three things above...... that is akin to having a door opened for us..... no? so then we can

SWITCH DOORS & take a live trade with an increased probability of our 20 pips(from current price) target being reached

of course these three outcomes are not each 33.33% likely to happen.. but can this be done in an EA to test whether there is any merit to the idea?

although counterintuitive...i do not see any reason why Monty halls logic should not apply equally well to the scenario i described above. Other than the obvious lol
  • #35
  • Jun 5, 2017 5:51pm Jun 5, 2017 5:51pm
Quoting dagoods
{quote} yes. exactly..... if we know what the price won't do... it's like knowing what is NOT behind door number 2..... for example lets take three doors and make them analogous to three possible outcomes for each hour of trading EU door number 1: price ranges and neither gains 20 pips to the upside nor does it decline 20 pips or more to the downside door number2: Price gains 20 pips to the upside door number 3: Price declines (goes short) 20 pips to the downside so, now we need a "Monty Hall" to open a door for us and tell us what price is NOT...
lol Ok now lets take an example...
of the 3 doors lets choose door number 1 (that price will range for an hour and not go long nor go short by 20 pips or more)

then we take a demo trade...
boom price goes short 20 pips......

Monty hall says we ought to now SWITCH DOORS, I.E. go long for 20 pips with a 20 pips stop

how very logical...go countertrend... that makes perfect sense right? shoot who wouldn't want to go long while price is going short...obviously must be a totally reliable method LOL

OK i'm obviously being sarcastic...but I'm actually really curious if there is anything to it that can be advantageous..... Monty is counterintuitive...maybe it would show us something worthwhile? any coders up fro making an EA?
  • #36
  • Edited 6:15pm Jun 5, 2017 6:02pm | Edited 6:15pm
example number 2.......

we choose door number 2 this time...namely that price will go long for 20 pis within an hour.... then we take our demo trade and wait an hour ....after an hour (which is akin to having Monty Hall open a wrong door for us)

Monty Hall (the demo trade) opens the door(he opens door number one this time) revealing to us that price has neither gone short 20 pips nor long 20 pips in that hour....

we therefore switch doors and go short with our live trade (opposite our original door of long) for 20 pips with a 20 pips stop


our theoretical odds according to the Monty Hall paradox & all other things being equal is 66.67% to win the trade


How is that not worth testing?

if it works even somewhat we have the moley quail...
  • #37
  • Edited Jun 6, 2017 7:26am Jun 5, 2017 10:29pm | Edited Jun 6, 2017 7:26am
Suppose I entered a trade at 'A' in the screenshot below, and I've just exited now. If I'd entered long, I would have lost money; short, I would have won.

But none of this has any bearing on how price will subsequently behave. If I enter again now, all that matters is what is likely to happen henceforth. The question is whether, according to my strategy, the situation in front of me now warrants another trade, i.e. represents a valid setup in its own right. That being so:
 If my edge comes from my entries, the question is one of timing and direction.
 If my edge comes from my exits, it depends on whether I cut losses quickly enough, or let profits run long enough, according to the dictates of my strategy in the current situation.
 Regarding position size, the question is whether the probabilities inherent in the current situation justify an increase (or decrease) in my 'normal' level of risk.

Entering the market again merely to recover recent losses has no math-based justification. The savvy trader bases his decisions on statistically proven price behavior, not his recent P/L, which the market takes no cognizance of. Applying a 'Montygale' with its doors, cars and goats is ultimately an attempt to impose one's own wishful MM onto an uncaring market.
Attached Image (click to enlarge)
Click to Enlarge Name: PPI 347.png Size: 28 KB
  • #38
  • Jun 5, 2017 11:14pm Jun 5, 2017 11:14pm
Quoting hanover
Suppose I entered a trade at 'A' in the screenshot below, and I've just exited now. If I'd entered long, I would have lost money; short, I would have won. But none of this has any bearing on how price will subsequently behave. If I enter again now, all that matters is what is likely to happen henceforth. The question is whether, according to my strategy, the situation in front of me now warrants another trade, i.e. represents a valid setup in its own right. That being so:  If my edge comes from my entries, the question is one of timing and...
I'm with Hanover on this. There is no way of mathematically shuffling odds regarding a future event such as a trade outcome. The Monty Hall problem applies to predictive modelling surrounding an event that has already occurred by altering the probabilities of success through the provision of additional information. This is effectively Bayesian problem solving.
  • #39
  • Jun 6, 2017 2:06am Jun 6, 2017 2:06am
Mingary says jump and you're all jumping! Pips_Cruiser is very right (https://www.forexfactory.com/showthread.php?p=9914889#post9914889).

The Monty Hall problem is about the decision taken by the host of the game (market) based on the first decision of the candidate (trader) which in turn gives additional information to open the next door (next trade). This would require that Mingary's first trade forces the market to react. In clear term he would have to trade big enough to shake the market and force a reaction.
No greed. No fear. Just maths.
  • #40
  • Jun 6, 2017 3:20am Jun 6, 2017 3:20am
Quoting PipMeUp
Mingary says jump and you're all jumping! Pips_Cruiser is very right (https://www.forexfactory.com/showthread.php?p=9914889#post9914889). The Monty Hall problem is about the decision taken by the host of the game (market) based on the first decision of the candidate (trader) which in turn gives additional information to open the next door (next trade). This would require that Mingary's first trade forces the market to react. In clear term he would have to trade big enough to shake the market and force a reaction.

yeah. i don't care if mingary is snake oil salesman or not.... irrelevant to our discussion of the math and or the application of monty hall as a trading MM technique.

I understand it does not make logical sense if we make it akin to predicting the future, but please remember it is a paradox. The whole reason it is called the Monty Hall paradox is because of how counterintuitive it is. Hanover. The game show does in fact PREDICT. the outcome of the game. NO? So why should the same not hold true if we apply the same logic to the markets? Math is Math. No?

There is nothing special about the game show. Monty Halls paradox is mathematics. Is it not? It is counterintuitive but it is in fact math and it does in fact work. Despite what we think if we truly "eliminate doors" we do in fact increase our odds over a number of trials. It is a proven verifiable fact in the monty hall game show, that you can in fact operate with a higher predictability by switching doors. so if we can Predict the game show, we should be able to predict the market. not with perfection, only with a higher probability. same same. math is math. no?
0 traders viewing now