by: Sherwin Ragos
The mean, median, and the mode are all measures of central location. These descriptive measures have bit differences from one another that are important for an statistician or a learner of statistics, general or business. When will you use the mean, the median, or the mode?
The first consideration should be the type of data collected. Is the data numerical or categorical? Numerical data are those that arise from numeric responses that have meaningful value. Categorical are responses in categories or classifications. Questions like: how many TV sets do you have at home, what is your weight in kilograms, elicit numerical responses. In contrast, questions like: what is your favorite color, what is the name of your pet, elicit categorical responses. If you have identified the type of data, you can now decide on what descriptive measures to be used.
When the data is numerical, you may use mean or median. But when the data is categorical, you may use the mode as a measure of central location. You might ask again, which one from mean and median to be used if the data is numerical? That is a perfect question. Mean is a measure of central location that is very sensitive to extreme values. Consider this example: 2, 8, 200. The mean of this is 70 and the median is 8. The difference between the two is obviously great. If the observations have extreme values or outliers, use the median because it will reflect a more realistic picture of the observations. Use the mean instead if there are no outliers.
