Why are we not using median at all times instead of mean?

Answer by Peter Flom:

Because the mean and median have different properties and sometimes we want the ones associated with the mean.

For example, in large samples from a normal distribution, the median has a larger standard error.  For another, the mean is the expected value.  For a third, the mean is influenced by outliers and, while that is often a justification for using median, sometimes we want a measure that is influenced by outliers.

Why are we not using median at all times instead of mean?

Leave a Reply

Your email address will not be published. Required fields are marked *