STATISTICAL BIAS
A restaurant has 5 reviews. All 5 are 5 stars. You think it is the best restaurant in town. You are wrong. The sample is too small.
QUICK ANSWER
The law of small numbers is the tendency to overgeneralize from small samples. It was identified by Daniel Kahneman and Amos Tversky. The bias explains why people make conclusions based on tiny samples. Small samples are unreliable. They produce extreme results. The law of small numbers is a common error in judgment.
The law of small numbers is simple: small samples mislead. You see a pattern in a few data points. You assume it is real. It is not.
A restaurant has 5 reviews. All 5 are 5 stars. You think it is the best restaurant. You are wrong. The sample is too small.
When making a conclusion, ask: what is the sample size? Is it large enough?
CORE IDEA
The law of small numbers is simple: small samples mislead. You see a pattern in a few data points. You assume it is real. It is not.
A restaurant has 5 reviews. All 5 are 5 stars. You think it is the best restaurant. You are wrong. The sample is too small.
The solution is to look for larger samples. Small samples are unreliable. They produce extreme results.
In the 1970s, Daniel Kahneman and Amos Tversky were studying how people make judgments under uncertainty. They found that people overgeneralize from small samples. They treat small samples as if they are representative.
The classic example is the gambler's fallacy. A gambler sees a roulette wheel land on black several times. They think red is due. They are wrong. The sample is too small.
Today, the law of small numbers is a foundational concept in behavioral economics.
The law of small numbers became famous because it explains why people overgeneralize. It is a common error in judgment.
The concept was popularized by Kahneman and Tversky. It is a cornerstone of behavioral economics.
Today, the law of small numbers is a foundational concept in statistics and psychology.
Kahneman and Tversky's research is the classic example. People overgeneralize from small samples.
A stock goes up for 3 days. You think it will keep going up. You are wrong. The sample is too small.
A product has 5 reviews. All 5 are 5 stars. You think it is the best product. You are wrong. The sample is too small.
A player scores 5 goals in 3 games. You think they are the best player. They are not. The sample is too small.
CONCEPT MAP
People expect small samples to behave like large ones.
Small samples create extreme results that later revert.
People ignore how much sample size matters.
Tiny selected samples mislead.
Vivid small examples feel representative.
Ignoring the importance of sample size.
No. It means you should be careful. Small samples can be useful, but they are unreliable.
No. It applies to everyday judgment. Anywhere you make conclusions from small samples.
You cannot eliminate it. You can only recognize it. The goal is to be aware of the bias.
When making a conclusion, ask: what is the sample size? Is it large enough?
Look for larger samples. Small samples are unreliable. They produce extreme results.
Be skeptical of patterns in small samples. They are often noise.
EXPLORE NEXT
Small samples create extreme results that later revert.
Small samples create extreme results that later revert.
People ignore how much sample size matters.
People ignore how much sample size matters.
Tiny selected samples mislead.
Tiny selected samples mislead.
Vivid small examples feel representative.
Vivid small examples feel representative.Small samples mislead. You see a pattern in a few data points. You assume it is real. It is not.
A product has 5 reviews. All 5 are 5 stars. You think it is the best product. You are wrong. The sample is too small.
Look for larger samples. Small samples are unreliable. They produce extreme results.
It leads to false conclusions. Small samples are unreliable. They produce extreme results.