Curriculum·S203 Chart Literacy and Evidence·about 40 min
Moving averages
By the end of this lesson you can
- →State what a moving average computes and derive its lag from the window length
- →Explain why a crossover is a statement about the past that arrives after the fact
- →Describe how the canonical positive result on moving average rules was overturned
- →Choose a window from your decision horizon rather than from convention
Sophomore · enrolled learners
This lesson opens with The moving average rules, and the correction that followed.
- What happened
- Brock, Lakonishok and LeBaron published a widely cited 1992 study applying 26 simple technical trading rules, largely moving average and range breakout rules, to about a century of daily Dow Jones Industrial Average data, and reported that the rules had predictive power. Sullivan, Timmermann and White revisited it in the Journal of Finance in 1999. They expanded the 26 rules into a far larger universe of rules drawn from the same families, applied White's Reality Check bootstrap to quantify and adjust for the data-snooping bias implied by selecting the best rule from that universe, and examined a subsequent out-of-sample period of roughly ten years. They found low profitability, which they interpreted as consistent with increased market efficiency.
- The decision point
- The original result was not fabricated and the rules had genuinely performed on that sample. What the correction established is that the 26 rules were themselves drawn from a much larger space of rules that practitioners had been exploring for decades, so the sample the study measured had already been used to select what would be tested on it. Once the size of that prior search was priced in and a genuinely unseen period was examined, the performance was not there.
What you will be able to answer
- →What is a moving average's lag?
- →What is a crossover, precisely?
- →How was the canonical moving average result overturned?
- →How should you choose a window?
Orientation and Year One are open: anyone can read them without an account. From Year Two onward the lessons are for enrolled learners, because progress through the later years only means anything if it is tracked against a record.
It is free. We do not sell the list and there is nothing to buy at the end of it.
Sources and review
- https://onlinelibrary.wiley.com/doi/abs/10.1111/0022-1082.00163
- https://www.kevinsheppard.com/files/teaching/mfe/advanced-econometrics/Sullivan_Timmermann_White.pdf
- https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1467-6419.2007.00519.x
- https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2308659
Confidence medium·Volatility low·Reviewed 2026-08-05·Owner unassigned
Contested
S203-04 uses the Sullivan, Timmermann and White result to teach regimes and the pricing of a search generally. This lesson uses it for the specific history of moving average rules. Keep the split; if a revision starts explaining Reality Check methodology here, that belongs in S203-04.
The interpretation that the out-of-sample decline reflects increasing market efficiency is the authors' reading and is one of several available. An alternative is that the rules were never predictive and the original sample was fitted. The lesson does not adjudicate.