I have been dipping my toes into the trading water as a bit of a hobby and like most new people doing badly. I have so far been 100% correct on the ultimate direction of my trades, but totally off in the timing - I guess this is a fancy way of same as saying I have been 100% wrong Rather than continue down this path I have stopped, read and thought - probably something I should have done this before starting Here are is what I have come up with so far. I would really like some feedback to see if I am on the track. 1. You need to find an edge to trade successfully long term. I suppose this is obvious, but the problem is how do you know that you have found a real edge and have not just data mined out a set of rules that seem to work? After all even if a movement series is truly random (eg radioactive decay), if you try enough rules combinations then you will find a set that appear to predict movement direction. 2. Any rule to future price correlation that can be mined out at a statistically valid level is obvious and has been arbed away. If I go data mining through millions of rules looking for a correlation with future price movements, then the p value of the null hypothesis would have to be so tiny that the rule would stick out like a sore thumb. This is similar to the same problem pharmaceutical companies face when they go data mining through the results of failed drug trial. It is very easy if you do this to find a "result" that shows the drug had an effect on some sub-population that appears to be statically valid, even when the drug is a sugar pill! It is for this reason that the FDA insists that any correlation result mined out of a drug trial are tested in an new independent trial before approval. 3. Rather than looking for correlations between market data and future prices I need to find the causes of price movements. Once a cause is found then a rule can be constructed and tested to see if it is statistically valid. 4. All publicly available causal data is already being used by at least one trader and so any edge that can be constructed from the data is already taken. 5. Finding an new edge require finding one or more unique data sets that are causal (or at least moved by the same underlying cause) of price movements. This might be best explained with an example. Imagine that I count the number of cars on each day in the car park of store and use this to predict the future earnings of the store. While earnings would not be perfectly correlated with the number of cars present, it is easy to see that if the car park is empty then there will be no customers and earnings will be poor. In reverse, if the car park is full of customers then sales will be good and earnings likewise all things being equal. Assuming that car counting is statically predictive of store future earnings, and earnings drive price movements, then I will have found a real edge. The major problem I can see with this approach is the either the predictive value of any unique data set will be so low that transaction costs will eat up any trading advantage, or the cost of gathering the data is so high that they exceed the possible extractable trading profits. The major advantage is I at least have a chance of finding a true edge not being exploited by anyone else. What are peoples thoughts?
im posting from my phone on the train so please excuse any typos. i enjoyed reading your post. i can tell that you think in a very qualitative way. i've been on the same path as you for the last few years. good luck.
I have found more than just a few times, that many people, myself included, tend to get caught up in the moment and buy a hot stock at the current price. You need to check the charts more thoroughly, and find the most consistant last level of support and set your entry price there. If that stock loves you as much as you love it, it will pull back to your position...if it does not, then screw the little sucker and move on to some security that wants to show the love a little more.
That's correct. That should be your starting point. Cause and affect. Nothing happens without a reason. Mining data without first thinking about cause is a waste of time, and is the ruin of most new traders.
Thanks for all the replies so far. It would seem that I am on the right track or a least heading the right general direction. To answer the question about what level is statistically valid, a p value of less than 0.05 is normally considered significant in science and medicine (ie there is only a 1 in 20 chance that the result is due to chance). The actually p value to use in trading is an interesting question. I guess the best way of thinking about what p value to use is to look at it from the perspective of trying to exploit a rule that is not real. It may be possible to use a rule with a higher p value as long as you are using more than one non-correlated rule in trading (ie if one rule is false then it only take out a percentage of your capital).
You may be thinking a little too much. But your post interests me. My remarks, which are nothing but personal opinions formed by years of involvement with the markets, pertain mostly to what is called discretionary intraday trading. I regularly trade the emini S&P intraday, and have lost enough money doing so from time to time to get quite an education. I also trade options and stocks but seldom intraday. For the typical retail trader with no inside information, no ability to make prices move in one direction or the other, and no ability to regularly buy on the bid and sell on the ask (or inside of these), short term trading is gambling. Although there is a difference between market gambling and casino gambling. In the casino it is impossible to turn the odds in your favor, but this is not true of gambling in the markets where there are times when the odds are in your favor. To succeed one has to be able to recognize these times and trade accordingly. The stock market has its own nature, Traditionally the market is a place for charlatans and hucksters of all sorts. This is as true today as it was a hundred years ago. Consequently, one has to look at short term price movements not as you would in an honest market that simply reflects natural supply and demand, but rather as in a dishonest market influenced by liars and cheats, all perfectly legal, though we have had plenty of the illegal sorts also. Consequently expect price movements to be quite often deceptive, and intentionally so. Major market participants with access to millions, or even billions, of capital, and using huge leverage with tiny per share, or per contract, trading costs regularly drive prices first one way and then another, and they do so in a deceiving manner. They know where the market is headed because they are going to make it head there. Your job as a retail trader is to determine what they are doing and jump aboard and get off at the nearest station (usually). As an example of how practical experience, as opposed to intellectual thought, can lead to an "edge" with a known cause, and thus to successful trades, I'll mention one little practical matter that all successful intraday traders are aware of and exploit. That is the matter of running stops. This is a very important aspect of emini trading but occurs in all short term trading. If you familiarize yourself with where many traders place their stop orders you will know ahead of time that when the market starts to move toward these locations with a certain gusto that it is very likely to continue on until the stops are taken out. You will naturally take advantage of this in both placing high probability "bets" and in avoiding bad places to place your own stops. So in summary, I would say that successful trading is more a matter of experience, patience and discipline than it is of intellect. It doesn't take a rocket scientist. There is tremendous interest in automated trading that has the huge advantage of removing human emotions from trading decisions. There are apparently two main types of autotrading going on. In one it is assumed that there are rules that can be applied mechanically and will lead, on average, to profits. Some traders seem to have success with this approach and that clearly implies some degree of regularity to the markets. The other type of automated trading is apparently based on automated market manipulation. Basically doing what major market participants have always done but refined and automated. There may even be a third category of automated trading, "high frequency trading." I know nothing about it except what i've read here on ET. Apparently it involves large numbers of trades for very small profits, and according to some here on ET, it involves jumping in front of orders, which would be "front running" which i always naively thought to be illegal. You may be the kind of person with a very analytical mind that could make a success out of autotrading. But either way you must approach short term price movements in the markets as being driven by fear, greed, market maker hype and legal manipulation -- not by any textbook theory or logical response to innate values of the underlyings being traded.
I think you are on the wrong track. As far as I know, p value has nothing to do with trading. I couldn't even finish reading your sentences.
Here's a way to develop a trading edge- Watch a stock 6.5 hours a day, 5 days a week, for weeks. Soon you will start to get a good feel for the 'personality' of it. Things like how the market makers or specialists trade it and the average type of trading activity, as well as how it reacts to anything and everything will become familiar to you... kinda like a family member or friend! Being familiar with a stock's movements 'is' a trading edge that increases your probabilities.
If you have a trader's mindset to begin with, then I'll assume you are looking for the largest moves within the shortest periods of whatever time frame you trade -- isn't that the ultimate (and most obvious) goal? What do you think causes prices to sometimes move with much greater velocity than normal? When you get down to the basic root of what makes prices move, you'll begin to realize that statistics are a rather roundabout and stale way of understanding the causes. Like pornography, you'll know it when you see it -- you don't really need to quantify the screen time of a pair of tits, do you?