The Meaninglessness of the Mean
The mean (average) or other central tendencies of a set of data is an internal construct that does not necessarily reflect reality. It is possible to determine the central tendency from any arbitrary collection of data as long as they vary on the same dimension. Even if applied to a relevant sample of data, the central tendency may be a poor reflection of data. A virtually infinite number of different collections of data may have the same central tendency and variance. This has very important implications when reasoning from studies reporting means and standard deviations. The same concerns apply to medians as the central tendencies and quartiles as the variability. When translating studies to the individual patient, the cumulative percentage (probability) function may be more helpful. There is a strong inclination to attribute some ontological status (reality) to measures of central tendency that can be misleading.