Normal Distribution (Bell Curve) Explained

Click through each step to understand the basics.

  1. What Is a Normal Distribution?

    A normal distribution is a bell-shaped data distribution that's symmetric around its mean β€” values close to the mean occur more often, and values further from the mean occur more rarely.

  2. Why It Shows Up So Often in Nature and Society

    Values like height, weight, and test scores, which are shaped by many small independent factors combining together, tend to cluster around an average, which is why they often approximate a normal distribution.

  3. What Is the Central Limit Theorem?

    The central limit theorem states that regardless of the shape of an individual data distribution, if you repeatedly draw samples and collect their averages, the distribution of those averages approaches a normal distribution.

  4. The 68% Rule

    In a normal distribution, about 68% of all data falls within one standard deviation of the mean.

  5. The 95% Rule

    About 95% of all data falls within two standard deviations of the mean, meaning most values cluster within this range.

  6. The 99.7% Rule

    About 99.7% of all data falls within three standard deviations of the mean, so values outside this range are quite rare.

  7. What Is a Z-Score?

    A Z-score expresses how many standard deviations a value is from the mean, which is useful for comparing scores from two different tests on a common scale.

Why the Bell Curve Matters in Statistics

Many natural and social phenomena β€” height, test scores, measurement error β€” tend to follow a symmetric, bell-shaped distribution centered on the mean. Understanding the normal distribution gives you an intuitive sense of where data clusters and how rarely it spreads out.

Finding Your Own Position Within the Distribution

If you want to know more specifically where you stand relative to others within a normal distribution, understanding percentiles is a natural next step.

Frequently Asked Questions

Does all data follow a normal distribution?

No β€” many kinds of data, like income, are skewed to one side. The normal distribution is just one of several distribution shapes that happens to appear relatively often in nature and society.

How should I think about values that fall outside 3 standard deviations?

Values beyond 3 standard deviations are so rare β€” only about 0.3% of the total β€” that it's worth considering whether they're measurement errors or genuine outliers with a special cause.