Measuring performance
Survivorship bias
The distortion caused by measuring only the things that made it, and ignoring the ones that failed.
How it works
Fund databases that drop closed funds, index histories that exclude delisted companies, and strategy backtests run on today’s constituents all overstate returns for the same reason: the failures are missing.
The effect is large. Estimates of the overstatement in fund performance databases commonly run to more than a percentage point a year.
Where it misleads people
A backtest of "the top 50 companies today" over twenty years is not a strategy anybody could have followed. It is a list of winners, tested on the period they won.
Related terms
- BacktestRunning a strategy over historical data to see what it would have done.
- Look-ahead biasUsing information in a backtest that was not actually available at the time.
- Equity risk premiumThe extra return investors expect from shares over risk-free government debt, for accepting the risk.
- IndexA rules-based list of securities used to represent a market or segment of one.
Mentioned in
More in Measuring performance
- Time-weighted return
- Sortino ratio
- Total return
- Sharpe ratio
- Tracking difference
- Risk-free rate
- Tracking error
- Realised profit and loss
All 29 Measuring performance terms · The full glossary, 433 terms
Educational reference only. Nothing here is investment advice or a recommendation to buy or sell anything, and tax treatment depends on your own circumstances and the country you are in.