Mathematician trader

[intradaybill]

Quote from RafaelAnderson:

For instance...:

I was thinking recently about the St. Petersburg paradox and the EMH...and the Kelly Criterion. I hope you are familiar with those concepts - they aren't that hard to understand....

Maybe not hard to understand but often difficult to apply properly in real life. For example, you can find various interpretations of %K, some are flat wrong. I think this article by my favourite guru Michael Harris is a good resource about %K and points out some of the difficulties in using it. IMO this paper also indicates the level of math a trader should be familiar with:

%Kelly paper

 

[hermit]

Without an understanding of how markets work, 'mathematical' trading is pure tactical hell.

 

[psytrade]

Quote from hermit:

Without an understanding of how markets work, 'mathematical' trading is pure tactical hell.

Thats very true in my experience. It would be like designing the assembly line before designing the car...

 

[Gabfly1]

Quote from hermit:

Without an understanding of how markets work, 'mathematical' trading is pure tactical hell.

How do markets work? I have never been able to figure that out in the years that I have followed them. The best that I have ever been able to do was...follow them. You sure as heck can't dictate to them or lead them. Not that I personally have any use for math in my own trading aside from adding and subtracting.

You refer to "pure tactical hell." But isn't successful and consistent trading largely the result of tactical success? Whether you choose to trade trends or fade them, isn't profitable trading largely about getting on the train when it's headed in your chosen direction? And given the uncertainly of market movement, aren't predictive models largely full of shit? (As with the talking head market pundits, it's essential to place their inaccurate predictions alongside their accurate ones for a comprehensive assessment of their true value.)

As I see it, engaging in an activity as laced with uncertainty as trading the markets is not unlike walking in the dark along an unfamiliar path. You keep walking carefully and not too aggressively until you reach an obstruction. When you reach inevitable obstructions, you move out of their way if you hope to continue. There is not a lot of strategy there, but a lot of tactics. Isn't that somewhat like trading, where you let your profits run, cut your losses short and don't trade too aggressively in order to survive in the long run?

Just a final comment on your reference to "understanding how markets work." While I have familiarized myself with price action over the years and have established for myself where a relatively low-risk entry may be, I have no idea how the markets work. They are constantly contradicting themselves and each other. You're not suggesting that you can predict a trend change in advance are you? And surely you don't believe in "measured moves."

 

[heypa]

Hey all you sophisticated complicated macho guys. IT ain't hard. When you dance with the market SHE ALWAYS LEADS! It ain't complicated you just have to follow and forget about leading.
If it's going up you can buy.
If it's going down you can sell.
Note you never have to get in but you should get out when the above happens.
Applies to swing trading only. Don't know about day trading.That requires leverage to succeed meaning exposure to ruin that I'm not willing to accept. It's a risk to return ratio that I can't handle.
Swing trading only requires arithmetic which strains my math capabilities.

 

[nitro]

If I may, let me rephrase your question: How can we tell at a 95% (99% ?) confidence level (reject/prove the null hypotheses) that some FX pair (stocks whatever) tend to move in certain % returns before changing direction, or persisting?

The added insight into this problem is to be very precise in your definitions. How are you going to represent "changing direction" in a mathematically precise way that can be fed into statistical machinery? If you think about it, changing direction entails creating an angle in price/time space. Ok, we have something that is quantifiable, angles.

Now comes the hard part. You can use standard statistics to try to see pattern in the returns data. However, it is important to understand that when you run any experiment, you are in essence testing two things, the hypotheses, and the tools you are using to test that hypotheses. It is very possible that the (mathematical) tools you use will be blind to structure in the data. For example, here is a book that describes 100 different statistical tests you can grind your data through:

http://www.amazon.com/100-Statistical-Tests-Gopal-Kanji/dp/0761961518

Imo the proper transform of your data is into spherical coordinates, and then run statistical tests on this data. For example, you could run your data through a V-test, sometimes called Modified Rayleigh. It is a test for randomness, checking whether angles in your data tend to cluster around a given angle. Perfect!

Another possibility is to do the sort of analysis that Chaos Theorists do, i.e., Rescaled Range analysis. But that is probably too coarse.

http://www.google.com/#hl=en&source=hp&q=rescaled+range+analysis&aq=f&aqi=g2&oq=&fp=e8d6ef47431c6a4a

Quote from Trish:

Considering randomness into an equation, I see prices move incrementally 5%, +2.5%, +1.25%, consolidate, pullback or move ahead in the same direction. I am not typing all the research I've done and used but wanted to know if there are any mathematicians/traders who understand what I am talking about.

The general targets help emotionally and sometimes show a range of 20 to 80 cents off the target. Depending on the time fame of a chart (or a high/low to start from), high volatility stocks might start at 10% while ETFs like SPY or DIA might start at 2.5% (+1.25%, etc.)

The reason I starting thinking about this was because a FX mentor told his student (a friend), to take 5% profit and exit a trade. Why 5%? Obviously there was profit and I started to look at a lot of price movements over time. Feedback from mathematical professionals is appreciated.

 

[riseluxx]

Quote from heypa:

Hey all you sophisticated complicated macho guys. IT ain't hard. When you dance with the market SHE ALWAYS LEADS! It ain't complicated you just have to follow and forget about leading.
If it's going up you can buy.
If it's going down you can sell.
Note you never have to get in but you should get out when the above happens.
Applies to swing trading only. Don't know about day trading.That requires leverage to succeed meaning exposure to ruin that I'm not willing to accept. It's a risk to return ratio that I can't handle.
Swing trading only requires arithmetic which strains my math capabilities.

I'd take this post as a joke...but yeah, it wa funny.

 

[Fat Tails]

Quote from RafaelAnderson:

For instance...:

I was thinking recently about the St. Petersburg paradox and the EMH...and the Kelly Criterion. I hope you are familiar with those concepts - they aren't that hard to understand, although the logic behind the St. Paradox is a bit conterintuitive and hence you need some decent logical thinking to understant it at first sight.

What, I was thinking for is a very simple model that one can use to generate high income this way.
Now...since it's a weekend almost i won't go further into more scientific terms, not to mention formulas or computer code(thogh believe it or not I can do both ...the formulas and the programming code...).

Anyway, here is the model:

An investor enters the market. She decides to buy Nasdaq 100 for example. On every deal she puts 30 pips limit order and -20 pips stop loss order. She uses this step many times...for example thousands of times....which is clearly a whole year - but...

What happens actually, using this extremely easy model of trading?

The idea is simple. In the St. Petersburd paradox, Nicolos Bernoully describes a game where a player doesn't bet anything but simply flat fee to enter the game. Then a fair coin is tossed and the player wins each time a tail occurs. When head occurs eventually the game ends and the player is left only with her gainings from the previous tails.
I hope you got the simple logic. The idea however is that, surprisingly this game is so promising that the player should enter the game at any price that is offered - because the potential of income is infinite.

Now, how this resemebles the stock market?

Suppose, every 20 pips are equal to one coin toss.
This if the investor wins 20, she wins one "tail". If however, she wins "40" - this is "two tails". Because the EMH is right however - the investor has a chance of 50% each 20 pips. Keep in mind that 20 pips is randomly chosen value, but even if the value was 200 pips, then the proability is yet 50%.

Just for fun: The St.Petersburg Paradox is an experiment that has an infinite expectancy. The problem is that the experiment is not real but requires a counterparty with infinite liquidity. Remember that LTCM had a valid concept of arbitrage but not enough money to play it out, as they used too much leverage (greed paired with false security derived from Gaussian distributions which should not be applied to non-random markets).

Your reasoning does not seem to include the loss expectancy in case the market moves against you. The St. Petersburg experiment is "tails - she wins, heads ends the game", the FOREX market is "tails - she wins, heads she loses - and she always pays the fees". This is a little difference.

To find a winning approach, a paradox does not help. If you can show that the distribution of returns is non-Gaussian, it is possible to find an edge. If an edge is easy to find, it is certainly difficult to trade. So this is what you can do:

As you are certain to lose, just trade a paper account and ask a friend to enter exactly the opposite trades. If your friend trades real money, you can then share the returns

 

[spindr0]

------------------------------------------------------------------------
Quote from heypa:

Hey all you sophisticated complicated macho guys. IT ain't hard. When you dance with the market SHE ALWAYS LEADS! It ain't complicated you just have to follow and forget about leading.
------------------------------------------------------------------------

Quote from riseluxx:

I'd take this post as a joke...but yeah, it wa funny.

Don't knock that post. becasue of it, I signed up for dance lessons!

 

[bighog]

Quote from Gabfly1:

How do markets work? I have never been able to figure that out in the years that I have followed them. The best that I have ever been able to do was...follow them. You sure as heck can't dictate to them or lead them.

Just a final comment on your reference to "understanding how markets work." While I have familiarized myself with price action over the years and have established for myself where a relatively low-risk entry may be, I have no idea how the markets work. They are constantly contradicting themselves and each other. You're not suggesting that you can predict a trend change in advance are you? And surely you don't believe in "measured moves."

.................................................................................

Gabflea has failed to learn how to play a game of odds. There in reality is no knowing "HOW MKTS WORK" Trading something is NOT figuring out how mkts work. If i was a baseball card trader i would care less how the cards were manufactured.

and yes fleabag, we can predict much more in mkts than you can.............How else would we be winners in a game of chance? Measured moves: say price is in a range, has a false breakout and comes back and travels THROUGH the range and breaks out the other side with conviction...........yes you can predict price will proceed the distance of the previous range as a profit target. Trade the odds because thats the best the mkt will offer traders. Deal with what yiou have to work with and quit being so negative. HOG OUT!!!!

PS: one final thought in this thread. math has its place in the world, rocket science etc, but trading something as easy as trends, etc requires only 6th grade math. Understand that and you will be far ahead of some math whiz. Trading is NOT reinventing the wheel. Trading is so easy it is difficult for the complicated.