How to keep in faith with a statistically profitable system? | Page 2 | Forex Factory

Options

Go to
Permalinks
Print Thread

Similar Threads

Statistically Infallible 11 replies

Statistically testing every indicator with my Genetic Algoritm 132 replies

A statistically rare pattern/anomaly - reversed? 9 replies

Are my 6-mth-old results statistically valid? 17 replies

What Constitutes a Statistically Significant Sample for Back Testing? 4 replies

Attachments: How to keep in faith with a statistically profitable system?
Exit Attachments

How to keep in faith with a statistically profitable system?

  • #21
  • Dec 31, 2010 4:21pm Dec 31, 2010 4:21pm
Well, in poker, the odds can be quantified because there are a set number of cards in a deck.... and counting cards makes it easy to quickly calculate a probability in one's mind based on what's left in the deck.

Unfortunately there is very little that can be counted to make decisions in trading.

I'm not saying people aren't profitable, but the information used to trade successfully is like finding a needle in a haystack.

Quoting hazelj80
just work out what the expactancy is. Also, focus on the process rather than outcome. the numbers will work for you in the long run.

this is how poker players keep their money and make more and the same thing great traders will tell you. just watch broke: the new american dream. the traders in there who have made millions will tell you that and so will great poker players who have made millions. makes all the sense to me. no need to overcomplicate this and try to say, "naw that doesnt work blah blah blah" maybe when you get to be a millionare...
  • #22
  • Dec 31, 2010 4:29pm Dec 31, 2010 4:29pm
this would basically mean that there are no such things as good or bad trades. that EVERY trade is a wildcard. that following a process would'nt work. i dont worry about outcome, i just worry about what i can control. and that how much i am willing to risk on a trade. The market does the rest. I'll agree.

yes, cards have a set number of cards but the markets and cards have one thing in common

you can make all the right decisions and still loose.

"There's 4 types of bets. there's bets you win, there's bets you loose. theres good bets and bad bets. you can win on a bad bet and loose on a good bet. we try to make good bets - Larry Hite
  • #23
  • Dec 31, 2010 4:40pm Dec 31, 2010 4:40pm
Here's how I see it:

The market is controlled by a handful of central bankers. You'd have to have insider information to know the huge buys/selloffs before-hand. And even with insider information, you'd have to know the COLLECTIVE plays of all bankers before hand.... not just one.

Now, what does a small fry like me do? I look at charts and try to place my stops based on historical ATRs.... knowing that a market's volatility is somewhat bound by the volume going into it. For example, EURUSD's volatility is much smaller that GBPJPY, so I'd have much tighter stops on EU.

But.... think about 2008.... when EU spiked thousands of pips in a month. I don't think I was the only one in shock when I watched that happen. "EURUSD, what are you doing? You've never done that in the history of your existence???"

So on and so forth.... Chaos, man. That's it. Every trade IS a wildcard in my book.... But at least I admit it's gambling
  • #24
  • Dec 31, 2010 4:46pm Dec 31, 2010 4:46pm
well, to that i say be the best gambler you can be and have a great trade year in 2011!
  • #25
  • Edited Jan 1, 2011 5:02am Dec 31, 2010 4:52pm | Edited Jan 1, 2011 5:02am
Interesting thread, hits home with all I'm currently working on. I have a math specific question here regarding the confidence interval calculation used in statistics to show how far off an observed population proportion is to the actual population. Can the 95% confidence interval be used when analyzing market data? As your sample size grows, wouldn't you expect the interval to converge? For example, if your confidence interval returned a 2% sampling allowance, with 1000 observations and an observed proportion of 85%, wouldn't you expect the sample as it grows to become less than that 2% figure?

I've made some interesting observations myself, I'd be pretty surprised to see the market change very much in some of the areas I've tested. For example, I did a quick study of simple Euro daily range stats and found some intriguing numbers. I'll include a snapshot of my findings. In my spreadsheet, "SD" means standard deviations. This study is based on the average range of 25 trading days. I found it interesting that over 95% of the observed days met or exceeded 50% of yesterdays average range. I used "yesterday" in the study because when a new day starts you really know nothing about what a day will bring.The information from yesterday is as close to today as you're gonna get. I've spent countless hours in excel doing all sorts of tests. I've been honing in on finding the highest probabilities and working out possible systems based on them. For example, based on my studies I've found that the odds favor the direction of a daily close if the close is above the high or low of the past day. So if price closes above yesterday's high today, there is a 70+% chance that yesterdays high will be met or exceeded today. Anyways, I'll shutup now, this is what I've been working on.
Attached Image
  • #26
  • Dec 31, 2010 4:53pm Dec 31, 2010 4:53pm
Yes buddy, by no means did I mean to nit-pick what you were saying... I just have my own views of forex that I openly and abrasively share.

Best wishes to you and your trades in 11 as well..... may you be on the winning half of the zero sum.
  • #27
  • Dec 31, 2010 7:59pm Dec 31, 2010 7:59pm
Quoting tdion
Here's how I see it:

The market is controlled by a handful of central bankers....
Ahh the big central bankers of countries and the Goldman Sachs masters of the universe controlling the market! They are the only ones that can figure this game out, they are the only ones that can make money, they are the only ones with the smarts to Buy AUD/USD at 0.9550 and sell it at 1.0250, they are the only ones with the smarts to short EUR/USD at 1.4275 and buy it back at 1.3000. See, those prices you saw on a chart didn't really exist, those prices are only for the central bankers of the world to transact at.

Us little poor guys, we got no chance. The central bankers and Goldman Sachs have got the ivy league educations, the quant junkies on their side, they got the High frequency traders, the statisticians and supercomputers, they've got access to information, they got the politicians in their back pocket, they have all this money to throw around. How could us little guys stand a chance against these market behemoths? If only those stops behind historical ATR's keep them safe, if only the world didn't go into global meltdown fears and EUR/USD makes 1,000 pip moves. If only we could know what collectively they are doing.

Sad trading is, I tell ya, the deck is stacked against us small fries. We got a low chance to pick tops and bottoms, we got low chance to develop extremely profitable trading systems. Dang that's why they opened up forex to us retail traders, the collective bankers of the world want to eat the big fries and us small fries too! They are damn hungry. Well lets quit the trading game and send them a pack of McDonald's fries instead!



Please... give us a break


This wasn't aimed at you tdion, but to the people out there who think they can't win at this game, hopefully to get some laughter and brighten up the situation for New Years!
Private message me for a link to my order flow website.
  • #28
  • Jan 1, 2011 4:35am Jan 1, 2011 4:35am
Wow grk, you make a perfectly sound and logical argument against trading, and then toss it out the window with sarcasm....

I don't know what to say. haha
  • #29
  • Jan 1, 2011 5:21am Jan 1, 2011 5:21am
Quoting tdion
Here's how I see it:

The market is controlled by a handful of central bankers. You'd have to have insider information to know the huge buys/selloffs before-hand. And even with insider information, you'd have to know the COLLECTIVE plays of all bankers before hand.... not just one.

Now, what does a small fry like me do? I look at charts and try to place my stops based on historical ATRs.... knowing that a market's volatility is somewhat bound by the volume going into it. For example, EURUSD's volatility is much smaller that GBPJPY, so I'd have...
As far as the interbank is concerned, you're a little off. You're right in that central bankers play a role in moving the markets, but the real players in the short term (>3months), is the financial customers of large dealing banks, mainly large spec funds. Market returns are always positively correlated with their orders. This has been demonstrated in many academic papers. Google Carol Osler or Richard K. Lyons.

Japan was intervening in the FX markets a while back, buying dollars, causing temporary prices spikes, but the market continued putting downward pressure on the pair. Intervention and central bank manipulation doesn't hold as much weight as you might think.

Now, it's fine and dandy for me to tell you that hedge funds drive the markets, but even then it's not entirely helpful. It's really difficult and expensive for the average small FX trader to get access to any useful order information aside from the FX futures market. Even good futures data is extremely expensive, I've heard of some participants paying thousands per month just for data. It's a game of who can be first. To my knowledge, that's all large scale HFT dealing operations.

My point is simply that it is possible to know what you are saying is unknowable, some guys do amazingly well with modest futures data feeds and programming backgrounds. It's all a matter of what tools you have at your disposal.

I think you are on the right track though, using statistics as something to lean on with your particular approach to the market. As I said in my new thread, I’ve been really humbled as of late, and I believe there are many ways to fish inefficiencies out of the market. It comes down to being creative and using the tools you have efficiently and correctly.

Happy new year,

Jim
  • #30
  • Jan 1, 2011 7:43am Jan 1, 2011 7:43am
Quoting hazelj80
i dont worry about outcome, i just worry about what i can control.
What you can control sometimes depends partially on the outcome

You can control your position size, but the next couple of bars (The outcome) can lead you to change your position size accordingly.

So in a sense, you have to care about both.

Regards,

Nader
  • #31
  • Jan 1, 2011 7:51am Jan 1, 2011 7:51am
Quoting grkfx
Ahh the big central bankers of countries and the Goldman Sachs masters of the universe controlling the market!
Actually, Goldman Sachs is not in the top 5 players in the FX market at all.

Deutsche Bank, UBS, Barclays, Citigroup & RBS are the top 5 players in the FX market.

That's not official data though, it's based on a Euromoney survey, but I think you can assume the findings to be close to reality.

Deutsche Bank has topped the list for the past 5 years.


Regards,

Nader
  • #32
  • Jan 2, 2011 12:26am Jan 2, 2011 12:26am
Quoting tdion
Wow grk, you make a perfectly sound and logical argument against trading, and then toss it out the window with sarcasm....

I don't know what to say. haha
Well, it is perfectly sound and logical argument against trading if you are just beginning and you hear all this talk about big players in the market, and conspiracies, and central banks, and all the other people who have all these other advantages over you.

Let me toss my post out the window with facts, instead of sarcasm. Because my post just doesn't stand up to the facts.

The buying AUD/USD at 0.9550 and selling it at 1.0250, as well as shorting EUR/USD at 1.4275 and buying it back at 1.3000, all those prices existed. They existed not just for central bank players, but for retail traders as well, even if you had above average spreads. You could of executed trades there. Nobody is stopping you from doing so. Not central banks, not the FED, not Deutsche Bank, etc. There was someone on the other side of those transactions. Maybe it wasn't a large order, but it was order flow nonetheless. Now you may say I exaggerated, how could you pick the top and bottom. Yes I exaggerated, but the prices existed and you could of executed trades there. The only thing stopping you from doing so is your own skill level, nobody else is stopping you. If you think the spot fx market is stacked against you, then you can go to futures market, commodities, stocks, bonds, etc.

Yes there are other market participants that have advantage over retail traders, but they are FAR from perfect. They take losses like many other traders, and can be caught on the wrong side of the market many times. These are human beings with emotions and are inefficient at best.

Even with all the advantages that other market participants have over you the market still can be mis priced every day! Every time the market makes a 30 pip move, 50 pip move, 200 pip move, or 1,000 pip move, that represents a mis pricing that can be capitalized on. Nobody is stopping you from placing amazing trades except your own skill level.

Remember, a lot of these banks are the same ones that got destroyed and took huge losses when the housing market collapsed. What happened to those ivy league educations, quant junkies, supercomputers, information advantage, politicians in their back pocket, deep pockets?

Well, if only they understood what generates order flow...

Have a great New Year FF Factory!
Private message me for a link to my order flow website.
  • #33
  • Jan 2, 2011 1:34am Jan 2, 2011 1:34am
Quoting in_drag88
So what do you traders think is the maximum numbers of consecutive losses can be tolerated for a profitable trading system?
What will you do if this number reached and you still don't have any idea what is wrong with your ts?
In theory, we should be willing to tolerate a losing streak that would send us broke, if the system has positive expectancy. Such negative variance is extremely rare, and if we're unfortunate enough to experience it, hopefully we've done very well in the mean time.

In practice, we usually have to consider capital preservation, so even if we perceive a system to be +ev, we'll have to drop it at some point (we can't ignore the possibility that the system has a negative expectancy).

I can't quantify when I would question a method or stop it. I can only talk about my own trading, and I would rather consider drawdown and the trades themsevles, than measuring performance in terms of wins and losses.

Quote
So, how can we measures one trading system's winning / losing performance? how much samples should we take?
I measure my trading by the decisions made during the trade, and less by the overall result (i.e. win or loss). Samples don't really matter to me. I'm not ignorant of mathematics, I'm just confident that I can tell if I'm trading well or not.

In poker, the best way to get an idea of a player's skill is not to analyse their winrate after thousands of hands, but to analyse a few dozen of their hands in detail. The same holds true to trading.
  • #34
  • Jan 2, 2011 1:55am Jan 2, 2011 1:55am
Quoting grkfx
Well, it is perfectly sound and logical argument against trading if you are just beginning and you hear all this talk about big players in the market, and conspiracies, and central banks, and all the other people who have all these other advantages over you.
Nice post.
  • #35
  • Jan 2, 2011 7:57am Jan 2, 2011 7:57am
Quoting Scotty B
It's a game of who can be first.
It's a game of who best positions themselves. I would argue that small but skilled traders are best able to do this, which would include good retail traders.
  • #36
  • Jan 2, 2011 12:47pm Jan 2, 2011 12:47pm
They got destroyed because of people defaulting on their house loans, not their inability to trade spot forex.

Quoting grkfx

Remember, a lot of these banks are the same ones that got destroyed and took huge losses when the housing market collapsed. What happened to those ivy league educations, quant junkies, supercomputers, information advantage, politicians in their back pocket, deep pockets?
What's very interesting is your remark about one's own skill. I'd like to share my outlook, as I am a quant. The EA I wrote does well in some market conditions, and gets slaughtered in others. I am gambling that the future market conditions will give me the chart patterns I need to succeed. So, I admit that I am gambling.

How can anyone that trades with any tool not have the same outlook? Andrews Pitchfork, Pivot Points, whatever.... they all fail in various market conditions.... and sometimes they win endlessly.
  • #37
  • Jan 2, 2011 2:22pm Jan 2, 2011 2:22pm
Quoting in_drag88
Dear fellow traders, i have a question stuck long enough and still can't figure it out by myself, maybe i didn't learn enough about probability math.
This question is appointed for any quants, please help me with this

Here we go :
Let's say we have test our system for once, say it 100 trades, and we got 90 winning trades and 10 losing trades (so we have simply 90% winning and 10% losing in percentage terms)
Then, we run the system in the live account, and suddenly,we have like 30 consecutive losses. According to our system it was 10% of failures,...
The results of my experiments suggest:
1. My tools yield 60% successful trades in a population of 100 trades
2. Consecutive losses or wins are very frequent
3. Most consecutive losses I experienced number 52 (in a block of 100 trades)
4. Most consecutive wins I experienced in a block of 100 trades are 34
5. I am still floating
6. The thing that keeps me floating is that I always risk a definite % of my LAST ACCOUNT BALANCE on each trade. This way, a winning streak of certain number of tades yieldS much more than a losing streak of same number of trades because winning streaks are incremental and each consecutive loss is smaller in $ terms.
7. Win,loss,win,loss i.e. alternate win/loss trades (that give net negative results even equal in numbers) are not too many as compared to the winning or losing streaks, because I am trading either in the right direction or in wrong direction but not in both directions.
8. YOU MAY NOT JUST CONSIDER THE PROBABILITY OF RANDOM OCCURANCE OVER A LONG-TERM IN CALCULATING WHAT YOU ARE TRYING TO CUALCULATE BUT ALSO THE IMPACT OF ONE BEING RIGHT AND WRONG IN THE DIRECTION. THIS MAKES THE DIFFERENCE.
The Thief of Wall Street
  • #38
  • Jan 2, 2011 3:06pm Jan 2, 2011 3:06pm
A fools COMMENTS:

Unless if it is an automated system.....made by some genius.....then any other system is based on perspective....

I have a momentum system that never worked for me......but it was made by a genius .....as I went through years of learning I came to that conclusion....Does it work ....I have no idea because I am not that type of trader......

The Truth from still a fool .....Is the PULSE.....THERE Is a PULSE.....check out a guy named mandelbrou......I think forex is a game he made.....

Only 5% of people in the market can follow this PULSE....the best are pattern traders....No not head and shoulders and double tops...patterns....but elliott pattern.......

5% people that means it's not YOU OR ME and HONESTLY I CHALLENGE anybody here to PROVE OTHERWISE THROUGH TRADING HISTORY......

Yes YOU CAN GET THERE, I AM TRYING.....WHEN YOU ARE THERE YOU will be making MILLIONS>......


So What I mean is there is an exact for everything and you can know it but there can ALSO BE MANIPULATION to these 5% of people through order flow and news manipulation.....DOES IT HAPPEN I think I will be able to say in a month.....

Humbly done it all and bean PROUDLY BEATEN and still trying....(don't worry no losses)
  • #39
  • Jan 2, 2011 3:43pm Jan 2, 2011 3:43pm
Quoting tdion
They got destroyed because of people defaulting on their house loans, not their inability to trade spot forex.



What's very interesting is your remark about one's own skill....
The example of the housing market shows that they can be grossly inefficient, and get destroyed in any financial instrument. There was a pretty huge transfer of wealth from the banks to the owners of the Credit Default Swaps, whether they were hedge funds, other institutions, individuals.

People try to rely on their 'tools' which heavily influences their own skill level. Why would someone want their own skill level be dependent/heavily dependent or constrained by moving averages, or other technical indicators? However, the human mind is an amazing thing, and no 'tool' should constrain it's potential.

Many tools do fail in some market conditions, and excel in others. But there are certain tools, certain concepts, certain foundations of every market that never fail, if you know how to put the pieces together. Things such as understanding what is generating order flow, and liquidity, etc. Once you truly learn them you can adjust the parameters, the criteria for trending markets, for ranging markets, for markets about to reverse. They never fail, as long as you are following the order flow that will be generated after you establish your position. In this situation the tools do not fail you, the tools do not constrain you, the only thing constraining you is your interpretation of the tools, your interpretation of the information and your own perception of the market, and what is driving it. Once you have the best 'tools', the best concepts, the best foundation of markets, knowledge of what generates order flow, the only thing stopping you is not a search for better tools, but your own capacity to properly assimilate the information of what will generate order flow.

Just my thoughts. I am not trying to change you from your quant view. I am just saying that their are tools out there that never fail, so long as you can attain the proper interpretation of the information that they are giving you. I dislike having a trading system that works only in one type of market, especially if it forces me to trade the market conditions that produce losses. So either I like to have a trading system that works in all markets, OR I can identify when the market is about to enter the market conditions that produce losses so I can stay out during that time. Then develop a way to determine when the market will enter the conditions that produce profits. It can be difficult, but doable. Why? Because there is someone on the other side of every transaction that will either make money or lose money. If they can figure it out then so can you.
Private message me for a link to my order flow website.
  • #40
  • Jan 4, 2011 5:16pm Jan 4, 2011 5:16pm
Quoting aediaz1
It would check my system again. One thing is for sure, you don't have a 90% chance for a win with this system. Depending on your style, having a high % win isn't essential to make a killing. I'm more than happy with 60% winning rate thanks to high R:R.

Below is a table showing probablity for consecutive loses within 100 trades with 90% chance for a win.
Thanks for the table, what was the formula you used to calculate it?
0 traders viewing now