Tools / free calculator
Which statistical test should I use?
Answer a few questions about your outcome variable and your design. You get the test your data actually requires, the assumptions it rests on, and a link to the calculator that runs it.
Sample size, distribution, cell counts and the level at which your data is clustered all refine the recommendation. If the stakes are high — a viva, a publication, a funder report — have the choice checked.
Talk to a statistician →
This calculator was checked by Elaine Halliburton, Professor of Applied Statistics
In short
How do I know which statistical test to use?
The test you need is determined by three things: the type of outcome variable (continuous, ordinal or categorical), what you are trying to do (compare groups, examine a relationship, or predict an outcome), and whether the observations are independent or come from the same participants measured more than once. Clustered data overrides all three and requires a multilevel model.
Further reading
The guide behind this calculator
More tools
Other free calculators
Send the data. Get a fixed quote.
Attach your dataset or just describe the project. A named statistician replies with a price and a deadline, usually within one working day.