What is sample size in trading?
In one line: Sample size is the number of trades, or other results, that a statistic like win rate or expectancy is based on. Bigger samples give more reliable numbers.
The idea
Flip a coin 10 times. You might get 7 heads. That doesn't mean the coin lands heads 70% of the time.
Trading stats work the same way. A few trades can show almost anything.
A simple example with numbers
Here's a rough rule for a method that truly wins about half the time. The wobble in your measured Win rate is about 1 ÷ √(number of trades).
| Trades | √ of trades | Wobble (about) | Win rate could read as |
|---|---|---|---|
| 10 | 3.2 | ±32 points | 18% to 82% |
| 100 | 10 | ±10 points | 40% to 60% |
| 400 | 20 | ±5 points | 45% to 55% |
So 10 trades can make a 50% method look terrible or amazing. At 100 trades the picture is much clearer. A math example, not a promise.
Notice: to cut the wobble in half, you need 4 times the trades.
Why it matters
Every number you track depends on it:
- Expectancy from 8 trades can swing from great to awful.
- A losing streak in your first 15 trades may just be noise.
- A "hot start" can trick you into sizing up.
That's why many traders want 50–100 trades on one set of rules before trusting the numbers. Practice on past charts makes that quick and costs nothing. See how to backtest a trading strategy.
A common mistake
Changing the rules every 10 trades. Then each version only has 10 trades. You never get a sample big enough to judge anything. Lock one version for 100 trades, log each one in your journal, and review after.
Count trades per rule set, not in total. 200 trades across 8 rule changes is really 8 samples of 25.
Questions
How many trades do you need to test a strategy?
Many traders aim for at least 100 on one fixed set of rules. More is better, and fewer rules make each sample go further.
Why does a small sample size matter in trading?
With few trades, luck dominates. Your win rate and average result can look very different from what the method really does.
Do practice trades count toward sample size?
Yes, if you follow the same rules and log them honestly. Replay practice is a fast way to build a sample without risking money.
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: