Does Intraday Technical Analysis in the U.S. Equity Market Have Value? (Marshall et al. (2008))

Does Intraday Technical Analysis in the U.S. Equity Market Have Value?

Read the paperopens doi.org in a new tab

What they found

The authors tested 7,846 technical trading rules (filters, moving averages, support and resistance, channel breakouts, and on-balance volume) on five-minute data for the SPDR S&P 500 ETF from 2002 to 2003. After correcting for data snooping using White's reality check and Hansen's SPA test, not a single rule was profitable. The best-looking rules in the raw results were exactly what you would expect to find by chance when testing thousands of variants.

See it drawn

Original diagrams for the ideas on this page. Illustrative, not real market data.

Support, resistance and the flip. Support is a price where buyers keep stepping in and the fall stops; resistance is a price where sellers keep stepping in and the rise stops. Once price closes above an old ceiling, that same level often acts as the new floor.

What you can use

On intraday index data, thousands of popular technical rules showed no edge once you account for how many rules were tried.
The rules that look best in a large search are usually the luckiest, not the best.
If you day trade a liquid index product with a mechanical indicator, this is the study to reckon with.

Caveats

Only two years of data on one very liquid ETF; results may differ for individual stocks, less liquid markets, or discretionary approaches. Does not test volume-profile or order-flow methods.

Tags: technical-analysis, intraday, day-trading, data-snooping

Summaries are our own reading of the paper, not the authors' words. Educational only, not advice. Discuss it in Book Club.