This statistics formula sheet keeps the standard formulas in one searchable place. It covers the mean, median and range, population and sample variance and standard deviation, the z-score, the empirical rule, probability rules and the least-squares regression line. A short note beside each formula says when to use it.
How to use the statistics formula sheet
- Type in the search box to filter by any word in a name, a formula or its note.
- Choose a topic to see one group instead of the whole list.
- Read the formula in the right-hand column and its meaning on the left.
- Press Print for a clean copy of whatever is shown.
What is in each topic
The statistics formula sheet is split into 4 topics. The table shows how many entries each topic holds and which ones they are, so you can jump straight to the right group with the topic box.
| Topic | Entries | What it covers |
|---|---|---|
| Centre and spread | 7 | mean; median; range; population variance; sample variance; population standard deviation; sample standard deviation |
| Normal distribution | 5 | z-score; empirical rule: one sd; empirical rule: two sd; empirical rule: three sd; standard error of the mean |
| Probability | 6 | probability of an event; complement; addition rule; independent events; conditional probability; combinations |
| Correlation and regression | 5 | correlation coefficient; regression line; slope; intercept; coefficient of determination |
Centre and spread
The mean is the sum of the values divided by how many there are. The population standard deviation is σ = √[Σ(x − μ)² ÷ N], the square root of the average squared distance from the mean. [1] When you only have a sample, the corrected formula s = √[Σ(x − x̄)² ÷ (n − 1)] divides by n − 1 instead of n. [1] That change is called Bessel's correction, and without it the sample figure tends to come out too low.
Variance is the square of the standard deviation. [1] The standard error of the mean is σ ÷ √n, and when σ is unknown the sample standard deviation s takes its place. [1] Range, the maximum minus the minimum, is the simplest measure of spread but depends only on the two extremes.
The normal distribution and z-scores
A z-score converts a value from a normal distribution with mean μ and standard deviation σ to the standard normal scale: z = (x − μ) ÷ σ. [2] It tells you how many standard deviations the value lies above or below the mean.
The empirical rule says that about 68 percent of values fall within one standard deviation of the mean, about 95 percent within two and about 99.7 percent within three. [2] It applies to data that is roughly normal; for heavily skewed data it can mislead.
Probability, correlation and regression
For equally likely outcomes, probability is favourable outcomes divided by total outcomes. The complement rule gives P(not A) = 1 − P(A), the addition rule is P(A or B) = P(A) + P(B) − P(A and B), and independent events multiply. Conditional probability is P(A and B) ÷ P(B). Combinations count the ways to choose r items from n when order does not matter. These are standard definitions and are listed as our own working.
The correlation coefficient r runs from −1 to +1. The least-squares line ŷ = a + bx has slope b = Σ(x − x̄)(y − ȳ) ÷ Σ(x − x̄)² and intercept a = ȳ − b·x̄, and R² = r² is the share of variation in y that x explains. Always plot the data first, because correlation does not prove cause.
Who this page helps
Students use a formula sheet to check a relationship while they practise problems, to build a revision page and to remember what each symbol stands for. Teachers can print a topic for a class handout, and anyone returning to the subject after a break can see the standard forms at a glance.
Tips for getting the most from the statistics formula sheet
- Decide first whether your data is a sample or the whole population, because that decides whether you divide by n or n minus 1.
- Plot the data before you calculate, so outliers and skew show up early.
- Round only at the end, and keep extra decimals in the middle steps.
Common mistakes
Most wrong answers come from using a formula outside the conditions it was written for, from mixing units, or from reading a symbol as something else. Check what each letter stands for before you substitute numbers, keep units consistent from start to finish, and estimate the size of the answer so an obviously wrong result stands out.
Where the entries come from
Each entry was checked against the sources listed below this article. Where a formula is a standard textbook definition that the sources do not state in that form, the article says it is our own working. Notation varies between textbooks, so if your course writes a formula differently, follow your course.
What this page does not do
It is a reference, not a calculator, so it will not work out numbers for you and it does not replace a worked example from your teacher. For calculations, use the linked calculators and compare their answers with your own working.
Printing and checking
Filter by topic before you print if you only need one section, and the printed page will be shorter. The notes are short on purpose, so keep your textbook or the official documentation open for the full detail and for anything that changes between versions.
What next
Use this often? Add Statistics F to your Home screen.
Frequently asked questions
What is in this statistics formula sheet?
Mean, median and range, variance and standard deviation, standard error, z-scores, the empirical rule, probability rules, correlation and regression.
When do I divide by n minus 1?
Use n minus 1 when you estimate the variance or standard deviation from a sample. Use N when you have the whole population.
What does a z-score tell me?
It says how many standard deviations a value is above or below the mean, so you can compare values from different scales.
Does correlation show cause?
No. A high correlation shows that two variables move together, not that one causes the other.
Was this tool helpful?
What went wrong?
We only receive the reason you pick, never what you typed into the tool.
Thanks for your feedback.