Evidence-Based Technical Analysis

Reply to Topic

Evidence-Based Technical Analysis

This book is about data mining to find trading rules and then verifying that the rules that were found are not co-incidences and are in fact valid rules that can be applied to current and future strategies. (I picked that up from the publisher's excerpt below.) Has anybody read this book and have any comments on it? (I have not yet read it?)

quote:
Evidence-Based Technical Analysis is a breakthrough book in that it rigorously applies the scientific method and recently developed statistical tests to determine the true effectiveness of trading strategies, rules or systems discovered by data mining. Traditional technical analysis – as currently practiced – is more like a faith-based folk art than a science, the author asserts. To move technical analysis forward, the author proposes a new type of technical analysis, which he calls: evidence-based technical analysis or EBTA. Unlike traditional technical analysis, EBTA is restricted to objective methods whose historical profitability can be quantified and then rigorously scrutinized. The author provides a new statistical methodology specifically designed for evaluating the performance of rules that are discovered by data mining, a process in which many rules are back-tested and the best performing rule(s) is selected. Experimental results presented in the book show that data mining is an effective approach for discovering useful rules. However, the historical performance of the best rule (s) is upwardly biased - a combined effect of randomness and data mining. Thus new statistical tests are needed to make reasonable inferences about the future profitability of rules discovered by data mining. Most importantly, in data mining case study the author evaluates over 6400 signaling rules applied to the S&P500 Index using these new tests. For technical analysts and traders, the book is a wake-up call to abandon subjective, interpretive methods and embrace an approach that is scientifically and statistically valid. For other traders, the rigorous testing of trading signals/rules may make their data mining efforts more productive and stimulate the development of new systems, signaling rules.

Page(s):
1

Some good questions Elite!

quote:
Originally posted by elite trader

rrl: What you say makes a lot of sense but there are still some problems with it. For example, what happens when there is no trend for the day and you get stopped out? What happens when you get on the wrong side of the trend and get stopped out? What happens when you get on the right side of the trend but a sudden move takes you out of the trade before the trend sets in?

These are standard problems in the two basic forms of trading. Following a trend OR trading the retracements. There is no answer to this question for any market. All markets will have periods moving sideways and periods trending on all time frames that are examined.

quote:
Originally posted by George Soros

quote:
Originally posted by elite trader

rrl: What you say makes a lot of sense but there are still some problems with it. For example, what happens when there is no trend for the day and you get stopped out? What happens when you get on the wrong side of the trend and get stopped out? What happens when you get on the right side of the trend but a sudden move takes you out of the trade before the trend sets in?

These are standard problems in the two basic forms of trading. Following a trend OR trading the retracements. There is no answer to this question for any market. All markets will have periods moving sideways and periods trending on all time frames that are examined.

The MP day types , ie. Dalton, help identify where the market is in this endless cycle of trends and consolidations. I personally view it as the market being in balance and out of balance. Dalton calls it being in value and outside of value.

It helps to have different strategies for trading in consolidation verses a trend. For example, moving averages work well in the trend phase. But moving averages fail during the consolidation phase. Conversely, oscillators work well in consolidation but suffer during the trend.

This is where years of market experience pay off, in being able to quickly and accurately identify and understand what the market is doing, ie. trending or resting. And being flexible enough to adapt to the actual market condition prevalent.

I know Market Profile and how it works (in theory) but I have never put it into practice.

Let me see if I understand you correctly. You take the value area that developed during the previous session. If the market today is trading inside that area you use a chart with an oscillator on it? If the market is trading above or below that area you use a chart with a moving average on it?

I am sure that what you are talking about is more complicated than my brief description but I am just trying to understand the basic concept of what you are saying at the moment.

quote:
Originally posted by George Soros

I know Market Profile and how it works (in theory) but I have never put it into practice.

Let me see if I understand you correctly. You take the value area that developed during the previous session. If the market today is trading inside that area you use a chart with an oscillator on it? If the market is trading above or below that area you use a chart with a moving average on it?

I am sure that what you are talking about is more complicated than my brief description but I am just trying to understand the basic concept of what you are saying at the moment.

For example, when the market is establishing a value area, moving averages will tend to flatten and converge, and oscillator signals will be profitable as price swings back and forth across the moving averages. Conversely, when the market is breaking out of value, the opposite will occur, oscillator signals will fail and moving averages will fan out in response to the volatility expansion and developing trend move.

As you point out, this is just one simple example, and the full MP paradigm provides a much more comprehensive view of market behavior.

From what I have seen a lot of this appears to be after the fact. If you have moving averages of 5, 10, 20, 40, 80 periods and you can see a fan then it is telling you what happened. The market consolidated and then at the beginning of the fan would have been the break out. The problem that I see is that you can see what happened but how can you trade it before it happens?

quote:
Originally posted by elite trader

From what I have seen a lot of this appears to be after the fact. If you have moving averages of 5, 10, 20, 40, 80 periods and you can see a fan then it is telling you what happened. The market consolidated and then at the beginning of the fan would have been the break out. The problem that I see is that you can see what happened but how can you trade it before it happens?

True, moving averages are lagging indicators, and respond to a price movement at 1/2 their length. So the short answer to your question is, don't trade the moving average, trade price.

Lets look at a generic example: let's use moving averages with lengths of 10, 20, 50, 100 and 200 bars on a 5 minute chart of the ES. We currently observe these moving averages are converging together, the 20, 50, and 100 are flatening out, and price along with the faster 10 ma is oscillating back and forth across them. We also observe volume is drying up. The moving averages are not predicting but rather confirming the current market situation. Based on this analysis, we can say value is currently being established. (In my terminology, I say the market is in balance, ie, buyers and sellers are balancing each other out). Also at this point, we can anticipate something (a future event) will inject a surge of new volume into the market (creating an imbalance) and drive price out of this value area to a new equilibrium price level. So we have a choice, trade the oscillators in value (current situation), or wait for price to breakout of value and trade with the trend to the new equilibrium level.

The hard part of course is trusting your analysis and indicators, especially so when the breakout from value actually occurs in real-time. This is especially true if your using oscillators to watch or trade market action during the establishment of value. When the price breakout comes, your oscillators will peg to an extreme level and stay there, thus causing hesitation (based on the conflicting signal) as the trend away from value becomes established.

I assume this is a day trading set up?
wont it be simpler with 20 and 50 MA?

quote:
Originally posted by pt_emini

Lets look at a generic example: let's use moving averages with lengths of 10, 20, 50, 100 and 200 bars on a 5 minute chart of the ES. We currently observe these moving averages are converging together, the 20, 50, and 100 are flattening out, and price along with the faster 10 ma is oscillating back and forth across them. We also observe volume is drying up...

When you talk about a chart set-up like this do you typically only look at the Regular Trading Hours (RTH) data or do you look at the continuous session?

Secondly, I notice that you talk about volume drying up. Have you used volume charts instead of time based charts to look at this sort of thing?

One of the problems that I have with moving averages on a time based chart is that you are giving the same weighting to the closing price of each time period irrespective of how many traders were active in that time period.

If, for illustrative purposes, 2 novice traders executed a trade between 12:00 and 12:05 then it is their price that we are using in that time period for the calculation of the MA. From 12:05 to 12:10 we have perhaps 100 experienced traders establishing a price.

Of course a volume chart does not solve this problem but it is more likely that in a 1,000 contract volume chart you will have the same mix of traders establishing a price.

Another way of getting around my bias against time based charts, or rather of making me happier to look at a moving average based on a time based chart, would be to use the average of the high and low instead of the closing price as the input into the moving average formula.

I apologize for semi-threadjacking this but I value your opinion.

quote:
Originally posted by inventor

I assume this is a day trading set up?
wont it be simpler with 20 and 50 MA?

pt is talking about creating an MA fan. For that you need 3 or more moving averages I believe otherwise you can't create a fan.
Yes I believe that we are talking about day trading here.

Not looking good for marriage if your win ratio is over 50%...