When should you use mean values versus median values in data analysis?

Use the mean when the data distribution is roughly symmetric and outliers are minimal, because the mean captures the central tendency of all values. Use the median when the data is skewed, contains outliers, or is ordinal, because the median is robust to extreme values and reflects the middle of the sorted data. For example, in salary data with a few very high earners, the median gives a better sense of a typical salary than the mean.