Mean Deviation of a Statistical List
Important: The stats package has been deprecated. Use the superseding package Statistics instead.
The function meandeviation of the subpackage stats[describe, ...] computes the mean deviation of the given data.
The mean deviation is defined as follows: the mean is first removed from the data, then the absolute value is taken for each item. The mean deviation is the mean of the resulting list.
The mean deviation is a measure of the dispersion of the data. For more information about such measures, refer to describe[standarddeviation].
When the arithmetic mean is not a suitable measure of the central tendency of the data, then neither is the mean deviation a suitable measure of the dispersion of the data. For more information please refer to the various measures of central tendency, such as describe[mean].
Classes are assumed to be represented by the class mark, for example 10..12 has the value 11. Missing data are ignored.
The command with(stats[describe],meandeviation) allows the use of the abbreviated form of this command.
The data 1,3,7 is more dispersed than the data 2,3,5, as can be seen as follows:
Here is an example where the mean deviation is not a suitable measure of dispersion. The data consists of 100 copies of the value 1, and 1 copy of the value 100000. This last value really has too much of an influence (it is likely that it was a bad reading of an instrument).
Download Help Document