# How can I quantitatively test the validity of momentum indicators?

I am learning about quantitative finance, and I am struck by how different it is from the techniques that make it into magazines and TV, particularly technical analysis. Specifically, if they say an indicator (RSI, TRIX, etc.) can predict even short term future prices, then you should be able to run some analysis to see if this was at least true in the past.

So my questions are:

If I wanted to learn the statistics used to calculate if there is any correlation between an indicator and any future price tendencies, what methods do I use?

Are any of these indicators known to have been verified quantitatively?

Remember that there is almost no point in predicting market movements if you cannot use it to trade and generate P&L. Thus, backtesting a stat arb strategy based on the indicator is best option.

Don't let yourself fooled by correlation or even directional forecast percentage accuracy as a few wrong predictions can blow your capital.

• You will need a set of entry and exit rules in addition to your indicator. (enter when indicator 1 is crosses 0.5 from below etc)

• Don't forget to account for all types of transaction fees you will have to pay.

If it's purely academic research you are doing then what I just said is of course not true.

• I would say that backtest is not enough. I would as well backtest your strategy on generated random walks and see how often the random walk underlying gives you better/worse results than the true underlying Jun 21, 2011 at 4:30
• A lot of random walks seam to have momentum periods. But I doubt it helps predict future returns Jun 21, 2011 at 4:31
• @RockScience good point, another test would be to see if indicator shows any difference compared to random sample. So what we are saying is that if we believe stocks follow random walk, then maybe momentum is equal to short term drift. Jun 21, 2011 at 20:43

You might want to check out the book Evidence Based Technical Analysis by David Aronson. In it he applies statistical techniques to determine whether certain technical analysis indicators and ensembles have any predictive power. It's an interesting read and should equip you with some ideas on how you might perform a similar analysis.

There is so much finance literature on this topic, I don't even know where to begin. Specifically on momentum, some of the earlier foundational papers are

Momentum has an entire page devoted to it at behaviouralfinance.net.

Lo, Mamaysky, and Wang (2000) conduct rigorous tests of a variety of popular technical indicators (although not specifically the ones you mention).

Cliff Asness's PhD thesis was based on Momentum and Value. AQR has a lot of interesting research.

http://www.aqrindex.com/AQR_Momentum_Indices/Momentum_Research/Content/default.fs

http://aqr.com/Research/ByTopic.aspx