See the FAQ: How to do a minimal reproducible example `reprex`

for beginners and the Homework FAQ.

There's a good explainer here and a short textbook with everything you'd want to know starting out.

In general, an `ANOVA`

takes the ratio of the between sample variance to the within sample variance as a basis for comparison to the Fisher probability distribution to answer the question *are the means of these two variables different* at some predetermined confidence interval? The null hypothesis is that they are not; if the test statistic exceeds the selected p-value, the null is rejected in favor of the alternative—that they are different. For multiple pairs of variables, with as few as 3 tests being considered, there is a 0.1426 chance of observing at least one significant result by chance, even if all of the tests are actually not significant. Approaches 0.99 with 14 groups. Post-hoc tests adjust to give a “global” significance level.