Benchmark
Last updated
A benchmark is the plain alternative a rule is compared with, such as holding the same assets and doing nothing. A rule's return only means something next to it.
How a benchmark is calculated
State the benchmark before the test. Tickfloor's benchmark for most tests is an equal-weight position in the same assets, rebalanced daily, with no costs charged against it. The comparison is the difference in annual return, with a p-value from a block bootstrap, then corrected for the number of tests run.
How it is read
A benchmark that has the same market exposure removes the part of the result that was just the market going up or down.
Common mistakes
- Comparing a rule with cash when it was in the market half the time.
- Picking the benchmark after seeing which makes the rule look best.
- Ignoring that the rule paid costs and the benchmark did not, or the reverse.
What Tickfloor tested
How we counted
Tickfloor's research desk has backtested 1,346 strategies, net of modelled trading costs. After correcting for the 1,778 tests run, 0 passed. That does not prove no strategy works. These are results from our older test setup, which was built before our current testing rules. They have not been redone under those rules.
Tests on Benchmark
- Momentum under realistic costs (study)
- Turn-of-the-Month Effect (claim test)
- Turnaround Tuesday (claim test)
Lessons that cover it
Related concepts
General information only. It doesn't consider your objectives, finances or needs. Tickfloor holds no financial services licence and never places trades.