The Math Behind the Market
Survivorship bias: is that success actually meaningful?
8 min · You mostly see the winners. The people who lost simply stopped posting.
- Survivorship bias
- Sample size
The stat
You mostly see the winners. The people who lost simply stopped posting.
Learn the number
Survivorship bias is what happens when you only look at the things that made it through, and forget everything that did not.
Screenshots of winning results are the survivors. The same person's losing weeks, and everyone who quit, are missing from the sample.
With enough people, extraordinary streaks appear by chance alone. If 10,000 people each flip a coin ten times, about ten of them will get ten heads — and any of those ten could sell a course.
The test is whether you can see the whole population, including the failures, before judging whether a result means skill.
Read the stat
10,000 people each make 10 coin-flip predictions. How many go 10 for 10 by luck alone?
- The chance of 10 correct calls in a row at 50% each is 0.5 to the power of 10.
- 0.5^10 = 1 ÷ 1024, or about 0.1%.
- 10,000 × (1 ÷ 1024) ≈ 9.8 people.
- So about 10 people go perfect with no skill whatsoever.
Around ten flawless records emerge from pure chance — and those ten are exactly the ones you would end up seeing.
Your turn
Someone shows a 12–2 record over two weeks. What would you need to see before treating it as evidence of skill?
Explain what it means
Apparent success is only meaningful against the full population of attempts. Without the failures, a winning record tells you nothing about whether skill produced it.
Make a prediction
Before checking a "hot" record, predict what it will look like after another 50 predictions logged in advance.
Review what happened
Records logged in advance regress toward ordinary. Records shown after the fact stay spectacular — because the unimpressive ones are never shown.
Check your understanding
0 of 4 correct
Every question has to be right for this lesson to count as complete. Miss one and you can try it again.