Use z-scores and the empirical rule to interpret data from a normal distribution.
Many real data sets (heights, test scores, measurement errors) cluster into the familiar bell-shaped normal distribution: symmetric, with most values near the mean and progressively fewer values further away. A z-score standardizes any value by measuring how many standard deviations it sits from the mean: z = (x - mean) / (standard deviation). A z-score of 2 means "two standard deviations above average" -- a way of comparing values across completely different data sets on the same scale.
The empirical rule (sometimes called the 68-95-99.7 rule) gives quick, powerful estimates for any normal distribution: about 68% of values fall within 1 standard deviation of the mean, about 95% fall within 2, and about 99.7% fall within 3. A z-score beyond +-2 is already unusual; beyond +-3 is rare.
Mastery looks like: They compute a z-score from a value (and a value from a z-score) and use the empirical rule to describe how typical or unusual a result is.
Common stumbles: Subtracting the mean and standard deviation in the wrong order inside the z-score formula; misremembering which percentage (68, 95, or 99.7) goes with which number of standard deviations.