Normal distribution
Normal distribution: the bell curve. With the default parameters (mean μ = 0, standard deviation σ = 1) its mean is 0 and its standard deviation 1. Use the simulator below to draw samples and see it take shape.
Simulate it
Change the parameters, then draw random samples. The bars are the samples; the line is the exact density. With more samples the bars settle onto it.
Samples to draw
What is the normal distribution?
The normal (Gaussian) distribution is the symmetric bell-shaped curve defined by its mean μ, where it peaks, and its standard deviation σ, which sets its width. Heights, measurement errors, exam scores and many biological quantities follow it closely.
Its importance comes from the central limit theorem: the sum or average of many independent small effects tends to be normal whatever the individual effects look like. That is why sample means, regression estimates and test statistics are approximately normal, and why z-scores, confidence intervals and most hypothesis tests are built on it.
Where it is used
- Heights, weights and other biological measurements.
- Measurement error and noise.
- Exam and IQ scores (IQ is scaled to mean 100, standard deviation 15).
- Sample means and sums, by the central limit theorem.
- Manufacturing tolerances and process control charts.
Shape and parameters
Symmetric, with the mean, median and mode all equal to μ. About 68% of values fall within one standard deviation of the mean, 95% within two (1.96 for exactly 95%) and 99.7% within three. Changing μ slides the curve; changing σ stretches it, and the area under it always stays 1.
What it assumes
- Symmetric data without heavy tails or strong skew.
- The values come from many small independent influences added together.
How it relates to other distributions
- Student's t distribution: With an unknown standard deviation and a small sample, use the t distribution, which has heavier tails.
- Log-normal distribution: A quantity whose logarithm is normal is log-normal.
- Chi-square distribution: The sum of squared standard normals is chi-square.
- Binomial distribution: For large n the binomial is approximately normal.
Common mistakes
- Assuming normality for skewed data such as incomes, waiting times or counts near zero.
- Using the mean and standard deviation of a heavy-tailed variable to judge how rare an extreme value is.
- Forgetting to standardise (z = (x − μ)/σ) before using a z-table.
How to work it out
- 1
The probability density function (the formula that gives the shape):
- 2
Its mean (the long-run average) and variance (the spread):
- 3
Worked example with the default parameters (mean μ = 0, standard deviation σ = 1): For the standard normal distribution, what is the probability of a value between −1.96 and 1.96?
LaTeX source of the formulas on this page
\[ f(x)=\frac{1}{\sigma\sqrt{2\pi}}\,e^{-\frac{(x-\mu)^2}{2\sigma^2}} \]
\[ \text{mean } \mu,\qquad \sigma^2 \]
\[ \text{answer} = 0.9500 \]At a glance
| Property | Value |
|---|---|
| Type | Continuous (measurements) |
| Parameters | mean μ; standard deviation σ |
| Possible values | all real numbers |
| Mean | 0 |
| Variance | 1 |
| Standard deviation | 1 |
| Example (mean μ = 0, standard deviation σ = 1) | For the standard normal distribution, what is the probability of a value between −1.96 and 1.96? Answer: 0.9500. |
How to compute it in Excel, Python and R
| Tool | Function |
|---|---|
| Excel / Google Sheets | =NORM.DIST(x, μ, σ, TRUE) (FALSE for the density, NORM.INV for percentiles) |
| Python (SciPy) | scipy.stats.norm.cdf(x, loc=mu, scale=sigma) |
| R | pnorm(x, mu, sigma) (dnorm, qnorm) |
Questions
What is the normal distribution used for?
The bell curve. Typical uses: Heights, weights and other biological measurements. Measurement error and noise. Exam and IQ scores (IQ is scaled to mean 100, standard deviation 15).
What are the mean and variance of the normal distribution?
Mean: mean μ. Variance: σ².
What does the normal distribution assume?
Symmetric data without heavy tails or strong skew. The values come from many small independent influences added together.
How do I calculate it in Excel?
=NORM.DIST(x, μ, σ, TRUE) (FALSE for the density, NORM.INV for percentiles)
How is the normal distribution related to other distributions?
Student's t distribution: With an unknown standard deviation and a small sample, use the t distribution, which has heavier tails. Log-normal distribution: A quantity whose logarithm is normal is log-normal. Chi-square distribution: The sum of squared standard normals is chi-square. Binomial distribution: For large n the binomial is approximately normal.