Mean and median use different information
The arithmetic mean uses the numerical size of every observation:
The median first orders the data and then identifies the middle position. Because of that difference, changing one extreme value changes the mean immediately, while it may leave the median unchanged.
A new example
Consider the ordered data
Both the mean and median are 6. Now replace the largest value, 8, with 28:
The median is still 6 because the middle position has not moved. The mean becomes
The single high value adds 20 to the total, which raises the mean by . Its exact distance above the other observations matters to the mean but not to the middle rank.
How this relates to skewness
In a right-skewed distribution, the long right tail contains unusually large values. Those values tend to pull the mean toward the tail, so the mean is often greater than the median. In a left-skewed distribution, unusually small values tend to pull the mean below the median.
This ordering is a useful descriptive clue, but it is not a complete proof of shape. Two summary numbers cannot reveal whether a distribution is bimodal, has gaps, or contains several clusters. A histogram, dot plot, or the underlying observations are needed to inspect those features.
Choosing a measure of center
Use the median when the goal is to describe a typical position and a few extreme values would make the mean unrepresentative. Use the mean when every magnitude should contribute to the summary, such as when totals or balances matter. The choice should follow the question being asked, not a rule that one measure is always better.
Related question
Apply this knowledge
Use the concept guide to understand the reasoning, then return to the complete question and worked answer.
If the Mean Is Greater Than the Median, What Does It Mean?Sources
These references support the core concepts and interpretation boundaries explained above.