What is survivorship bias in trading?
In one line: Survivorship bias is drawing conclusions only from the people, funds or stocks that are still around, while ignoring the ones that dropped out.
The idea
You only hear from the people who stayed. The ones who quit go quiet.
So the stories you see are a skewed slice of everyone who tried.
A simple example
Imagine 1,000 people try the same strategy for a year. Most stop. 20 do very well by luck alone.
Those 20 post about it. The other 980 don't.
From the outside, it looks like "everyone who tried this did great." You're only seeing the survivors. An illustration, not real data.
It shows up in backtests too
Say you test a strategy on the stocks in an index today. Those are the companies that grew and stayed. The ones that shrank, merged or went bust were removed from the list years ago.
Your test never sees them. So it looks better than it would have been in real time.
Good test data includes stocks that were later removed. Ask your data source if it's "survivorship-bias free."
Why it matters
Survivorship bias makes things look safer and easier than they are:
- Trading stories and screenshots show the top, not the whole crowd.
- Funds that closed drop out of performance tables.
- Backtests on today's winners overstate results.
None of that tells you what's likely for you. Your own tested record does. See how to backtest a trading strategy.
A common mistake
Copying someone because they "made it." You can't see how many others did the same thing and didn't. And their results can't be copied. See why copying signals isn't a shortcut.
Before trusting any result, ask: who isn't in this picture?
Questions
What is an example of survivorship bias in trading?
Only seeing posts from traders who did well with a method, while the many who tried it and stopped never post at all.
How does survivorship bias affect backtesting?
Testing only on stocks that exist today leaves out the ones that failed, which can make a strategy look better than it really was.
How do you avoid survivorship bias?
Use test data that includes delisted stocks, count everyone who tried a method rather than only the winners, and trust your own sample size of logged trades.
Want the next step? We'll walk you through it.
Four free lessons by email, one every few days — each with a 10-minute exercise on a real chart.
Send Me the Free Lessons 4 short emails · No spam · Unsubscribe anytimeOr see the whole method, step by step:
See What’s Inside the Course Try everything free first. Decide when you're ready. · Open the free chart tool (works in the TradingView phone app)One chart idea a day, in plain English. Follow along: