Statistical power

The probability a test will detect a real effect of a given size, if one truly exists, given your sample size.

Statistical power is the probability that a test will correctly detect a real effect, of a given size, if one actually exists. 80% power is the conventional planning target — meaning if the true effect is exactly the size you designed around, you have an 80% chance of seeing a statistically significant result, and a 20% chance of missing it entirely even though it's real.

Power is a function of sample size, the effect size you're trying to detect, and your significance threshold — which is exactly why sample-size math has to come before a test launches, not after it disappoints. See sample size math for multivariate tests, honestly for the full worked calculations.