Choosing an Appropriate Measure of Central Tendency

If it is at all possible, you should attempt to find all three measures of central tendency. This is because you want to have as much information about the subjects you study. However, if this is not possible, then there are situations in which the mean, median, and mode have their specific "advantages".

The mean is ordinarily the preferred measure of central tendency. The mean is the arithmetic average of a distribution. The mean presented along with the variance and the standard deviation is the "best" measure of central tendency for continuous data.

There are some situations in which the mean is not the "best" measure of central tendency. In certain situations, the median is the preferred measure. These situations are as follows:

• when you know that a distribution is skewed
• when you believe that a distribution might be skewed
• when you have a small number of subjects

The purpose for reporting the median in these situations is to combat the effect of outliers. Outliers affect the distribution because they are extreme scores. For example, in a distribution of people’s income, a person who has an income of over a million dollars would dramatically increase the mean income whereas in reality, most of the people in the distribution do not make that kind of money. In this case, the median is the preferred measure of central tendency.

The mode is rarely chosen as the preferred measure of central tendency. The mode is not usually used because the largest frequency of scores might not be at the center. The only situation in which the mode may be preferred over the other two measures of central tendency is when describing discrete categorical data. The mode is preferred in this situation because the greatest frequency of responses is important for describing categorical data.

Joe Boyle
Updated June 5, 1997