Survivorship Bias
Survivorship bias is drawing conclusions only from what survived — successful traders or companies still listed — while ignoring the failures that disappeared.
If you only study the winners still standing, the game looks easier than it is. Survivorship bias happens when failed funds, delisted stocks or blown-up traders drop out of the data. The remaining results look better than reality, misleading backtests and performance comparisons.
- Reading time
- 3 min
- Also called
- Survivor bias, Survivorship effect, Backfill and survivorship
- Updated
Survivorship bias in plain words
Published hedge fund return indexes suffer from an important distortion: survivorship bias.1
Funds that perform badly struggle to raise money.1 So they tend to shut down, and only the winners stay in the database.1
Survivorship bias and look-ahead bias are two of the behavioural pitfalls to guard against when backtesting.2
How to avoid survivorship bias
Ask what is missing
Check whether failed or delisted assets were removed.
Use full data
Use data that includes funds that closed, not just those still running.3
Fix the universe by date
In Backtesting, use the list of assets that existed at each past date.
Doubt success stories
Winning traders are visible; the ones who quit are not.
Compare with all funds
Judge any fund or signal against the full peer group.
Check your own records
Keep losing systems in your Trading Journal rather than deleting them.
Worked examples
Example 1 — Survivor-only backtest
Inflated testA hypothetical stock strategy is tested only on today's index members.
| Backtest return | +12% a year |
| With delisted stocks | +7% a year |
Leaving out failures leaves only the more successful names, inflating the test.1
Example 2 — Fund database
OverstatedA hypothetical fund list drops every fund that closed.
| Surviving funds avg | +9% |
| All funds avg | +6% |
Unsuccessful funds tend to close, so survivor averages overstate typical returns.1
Example 3 — Copying a 'guru'
Hidden losersA hypothetical trader copies a strategy shared by a few big winners online.
| Visible winners | Few |
| Copy result | −8R |
High attrition with little evidence of differential skill means the winners may simply be survivors.3
Survivor-only vs complete data
| Aspect | Survivor-only data | Complete data |
|---|---|---|
| Includes failures | No | Yes |
| Average returns | Overstated | Realistic |
| Risk picture | Too rosy | Fuller |
| Backtest reliability | Low | Higher |
Where survivorship bias appears
Backtests
Testing on today's members only in Backtesting.
Fund returns
Comparing averages that skip closed funds.
Trading stories
Judging a Trading Strategy by visible winners.
Edge claims
Overrating a Trading Edge from biased data.
Advantages and disadvantages
Advantages
- Awareness leads to fairer tests.
- Encourages complete data.
- Tempers unrealistic expectations.
- Improves strategy comparisons.
Disadvantages
- Complete data can be hard to get.
- Point-in-time data costs more.
- The size of the bias is hard to know.
- Success stories remain persuasive.
Going deeper
Read as far as you need. Each level builds on the one before it.
Why it happens
Beginner
Struggling funds can't attract money, close down and drop out of the data, so averages look better than reality.1
Research evidence
Intermediate
Studies that include dead funds find very high closure rates and little evidence that some managers are reliably more skilled.3
In backtesting
Advanced
CFA Institute names survivorship bias alongside look-ahead bias as issues analysts need to pay attention to in backtesting.2 Point-in-time data and large samples help.
Common mistakes
Testing on current members
Failures vanish.
Trusting fund averages
Closed funds are missing.
Copying visible winners
Losers are silent.
Deleting failed systems
Your own records get biased.
Check your understanding
Test yourself before moving on. Each answer comes with an explanation.
Key points to remember
- Missing failures make results look better.
- Closed funds leave survivor databases.
- Use complete, point-in-time data.
- Visible winners may be lucky survivors.
- Keep your own failed systems on record.
Frequently asked questions
Does survivorship bias only affect funds?
How big is the effect?
Is it the same as look-ahead bias?
Further learning
- Backtesting
Testing fairly.
- Win Rate
Reading results fairly.
- Trading Edge
Checking claims.
- Expectancy
Realistic averages.
Sources
This article is written in our own words. The sources below support the specific facts, rules and figures marked with a number in the text. Links open the original publisher’s page.
- Federal Reserve Bank of Atlanta. Hedge Funds: Risk and Return (Malkiel, 2006 Financial Markets Conference) (opens in a new tab) Checked .
- CFA Institute. Backtesting and Simulation (opens in a new tab) Checked .
- NBER. Offshore Hedge Funds: Survival and Performance 1989-1995 (Working Paper 5909) (opens in a new tab) Checked .
Educational content, not financial advice. Examples use hypothetical prices and simplified costs; actual fees, margin rules and regulations vary by broker, market and country. We are not affiliated with any publisher linked above. Last reviewed . Report an error or request a source credit.