ANOVA
A test of whether three or more groups' averages differ, comparing the spread between group means with the spread within groups.
Three landing pages give three pairs to compare (A-B, A-C, B-C). Each t-test has a 5% chance of a false alarm, so running all three gives about a 14% chance that at least one "wins" by luck alone. With ten groups there are 45 pairs, and the chance of at least one false alarm is about 90% (treating the tests as independent). ANOVA (analysis of variance) asks one question instead: is there more spread between the group averages than the spread within the groups would explain?
Try it now
Ask: how many groups, and is each person's answer a number, a yes/no, or a category?
Learn it properly
More tests: groups, categories, relationships · Choose a test, ANOVA by hand, chi-square on counts, Pearson vs Spearman, one-sided tests. About 40 minutes.
Other terms from the same lesson
- chi-square test: A test of whether two categories are related, from how far a table's counts are from those expected if they weren't.
- F statistic: ANOVA's ratio of between-group to within-group spread, each divided by its degrees of freedom; near 1 when the groups are alike.
- one-sided test: A test that looks for a difference in one direction only; it's valid only when that direction was chosen before seeing the data.
- Pearson correlation: A number from -1 to 1 measuring how closely two numbers follow a straight line together.
- Spearman correlation: Pearson's correlation computed on ranks: it measures whether two numbers always move the same way, and resists outliers.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.