Did it actually cause it?

How we actually do it

• We pick the method from your data, not from a menu. Your file is profiled first — group count, distribution, variance — and the test follows from what's actually there.
• Assumptions are tested and reported, not assumed. When one fails we switch method and say so in the write-up rather than quietly carrying on.
• You get an effect size, not just a p-value. 'Significant' on 40,000 rows can still be too small to act on, so magnitude and its confidence interval are always shown.
• Every number traces back to code. The R that produced each figure ships with the report, so anyone can re-run it.

See it on real data

That is the actual report this analysis produces — not a mock-up. Every analysis on this page delivers the same shape of output on your own data.