AB SHARK

Test picker

Upload your A/B data. The picker inspects shape, balance, and outliers, then recommends the test that fits best — and hands off to the analyzer with the form pre-filled.

Upload CSV

One row per visitor. Stored on the server for up to 1 hour, then deleted.

Upload a CSV and pick a variant + value column. The test picker will recommend a test and show diagnostics here.

Frequently asked questions

How does the test picker choose a test?

The picker inspects your raw data: it detects 0/1 columns as binary outcomes and otherwise treats the column as continuous. For binary outcomes it recommends a two-proportion z-test when the sample size is large and Fisher's exact test for small samples. For continuous data it recommends Welch's t-test when the distribution is approximately normal, and a rank-based test like Mann-Whitney U otherwise.

What if the recommended test is not implemented in abshark?

The picker always recommends the statistically best-fit test, even when abshark doesn't ship that test yet. When that happens the recommendation explains why and offers the closest implemented alternative so you're never stuck.

What diagnostics does the test picker produce?

Per variant: sample size, mean, median, standard deviation, min/max, quartiles, a histogram, a box plot with IQR-fence outlier counts, a normal QQ plot, and a Shapiro-Wilk normality result (capped at n=5000, where the CLT covers inference).