Statistical Test Workbench
Run a t-test to compare averages. Choose one sample, paired measurements or two groups, then review the results and assumptions.
Which t-test should I choose?
Use one-sample to compare a sample mean with a specified value. Use paired for aligned measurements on the same subjects. Use Welch for two independent groups without assuming equal variances. A p-value does not measure effect size or prove a hypothesis.
Your result
A little clarity, right here.
Start with your own content or load the example. Your result will appear here.
Three simple steps
How to use Statistical Test Workbench
Choose your input and adjust the options.
Review the preview and run the tool.
Download the result and keep your original.
Common questions
Good to know
Understand the result.
Keep the original.
Is this tool free, and are my files uploaded?
This tool is free with no account required. The work happens in your browser. Your input and files are not sent to a processing server.
What are the limits and details?
At least two finite values per sample, up to 50,000 values. Tests assume independent observations (independent pairs for paired tests) and approximately normal sample means. Zero-variance standard errors are rejected. Confidence intervals are two-sided and shown separately from the selected test direction.
Limits: 500,000 characters per text field; files up to 20 MB each, 10 files and 50 MB total. Processing stops after 30 seconds.