Let us take a look at technical analysis, which is used by many to make a profit by predicting the stock market.
Technical analysis is a set of tools used to analyze the movement or behavior of a stock or index instead of the facts surrounding the company or the economy, which is usually used when trying to predict where stocks are heading.
Some use trend lines or channels to figure out the trend, some use resistance and support lines to see where there will be a lot of buyers or sellers.
One of the problems with this approach is that in any given chart, even randomly produced, you will in hindsight easy spot a trend. Of course if a chart is randomly produced you will not be able to forecast the next move. So how come you can do that in the stock market?
People in the field of statistical analysis are often dogmatically blindfolded. They might claim that since so many people are using it, it cannot be wrong. Or they know successful people who are using it, or even use it successfully themselves.
However, this type of reasoning suffers from strong statistical bias, such as survival bias, where only the winners tell the story about how good it works. While the losers go back to their jobs and usually do not speak so much about their failure. It could also be that since some only use a long strategy only, in a rising market. In other words they would have done well be just buying and holding.
Now let us look at the scientific research in this field. Oh yes, there is quit a bit of research, but strangely enough it never reaches the believers.
In the research paper “On the Analogy Between Scientific Study of Technical Analysis and Ethnopharmacology” via CXO Advisory they write:
There are four areas of similarity between folk medicine and technical analysis:
- Both have foundations in folk science, with most claims proving false when subjected to rigorous scientific testing;
- Both have strong potentials for statistical bias, the placebo effect for folk medicine and data snooping for technical analysis;
- Both boast commercial popularities that support large markets for products/services; and,
- Both are possible sources of scientific knowledge (for pharmacology and financial economics, respectively).
The essential lessons from folk medicine for testing of technical analysis are:
- The study of technical analysis should mirror the rigor of drug evaluation methodology (e.g., randomized, double-blind, placebo-controlled trials involving homogeneous populations);
- The study of technical analysis should include greater emphasis on explaining the behavioral mechanisms underlying hypothesized market inefficiencies; and,
- There should be a independent peer-reviewed journal devoted to the rigorous testing of technical analysis.
In another scientific peer-reviewed paper, “Evidence-Based Technical Analysis: Applying the Scientific Method and Statistical Inference to Trading Signals” via CXO Advisory it says:
David Aronson opens with two contentions: (1) “much of the wisdom comprising the popular version of TA does not qualify as legitimate knowledge;” and, (2) “TA must evolve into a rigorous observational science if it is to deliver on its claims and remain relevant.”
None of the 6,402 rules tested on the S&P 500 index, after adjusting for data mining bias, generate statistically significant outperformance. More complex/nuanced rules, or other financial data sets, might indicate abnormal returns.
From the paper “Identifying Noise Traders: The Head-And-Shoulders Pattern in U.S. Equities”, where a commonly used technical pattern called “Head and Shoulder” the following is summed up by CXO Advisory:
The author determines that head-and-shoulders pattern trading exists but is on average unprofitable, mistakenly interpreting randomness as information.
Is technical analysis worthless?
Yes and no. It is if you do not have a quantifiable edge. That means that you must have a statistical edge before you trade or invest. A rigorous back-test of your hypothesis must be done. What most people seem to do is that they are guessing or using some false authorities providing them false information about what is supposed to give them an edge.
Not even if you are back-testing your strategies to gain a statistical edge you are guaranteed future winnings. In fact there will be long periods, minutes, hours, days, or a lifetime where a historically proven winning strategy will become a losing one. To avoid this, look over your strategies often and see if they are obsolete in the current environment, and use many different strategies to diminish the risk.
The human brain is not particularly well wired for finance and trading. That is the reason why not even central bankers or countries know how to run their economies.
Most of the argument on technical analysis above can also be applied to fundamental analysis such as P/E-ratios, the FED-model, dividends-yield, et cetera, but that is for another article.
I would say that probably more than 90% of the “knowledge” out there on trading and investing is bogus, so watch out. Maybe even this article is, so always use your most critical judgment, and if you cannot, staying out of the markets will win you do most in the long-run.
Good luck! (or rather stay out of the luck part and in to the field of competence instead)