Glossary
Backtest
A test of an investment rule on past data, to see how it would have done.
A backtest applies a rule, such as "buy the stocks that score above a threshold and rebuild the list every quarter", to historical data and records the hypothetical result.
Backtests are easy to get wrong without meaning to. The usual mistakes are using data that was not available at the time (look-ahead bias), leaving out companies that failed (survivorship bias), ignoring trading costs, and trying many rules until one looks good.
A backtest result is hypothetical. Only results recorded before the fact, on data that did not exist when the rule was built, can confirm it.
Related terms
- Survivorship bias: The error of studying only the companies that still exist, which leaves out the ones that failed.
- Look-ahead bias: Using information in a test that was not yet available on the date of the decision.
- Drawdown: The fall from an investment's peak value to its lowest point before it recovers.