Mean, mode and median. Deviation and standard deviation
The mean is x̄ = (x₁ + … + xₙ)/n; for a frequency table x̄ = (n₁x₁ + … + nₖxₖ)/n. The mode is the most frequent variant (there may be several modes). The median is the middle value of the variation series: the (n + 1)/2-th term if n is odd, and the average of the n/2-th and (n/2 + 1)-th terms if n is even. A single large value changes the mean noticeably but hardly affects the median. The range is the difference between the largest and smallest variants. The standard deviation shows how widely the data are spread around the mean: sₙ = √(Σ(xᵢ − x̄)²/n), and for a frequency table √(Σnᵢ(xᵢ − x̄)²/Σnᵢ). If all values are equal, sₙ = 0; the greater the spread, the greater sₙ. For data grouped into intervals the mean is found approximately using the midpoint of each interval.
| Quantity | Rule |
|---|---|
| mean | x̄ = (x₁ + … + xₙ)/n |
| mode | the most frequent value |
| median | the middle value |
| range | max − min |
A PE teacher orders team kits for 24 pupils: size S for 4, M for 10, L for 7 and XL for 3. The mode is M, so most kits are ordered in M. Working out a numerical “average size” from labels such as S, M, L and XL makes no sense: for data like this the mode is the useful measure.
Store and warehouse managers identify the most demanded item (the mode), doctors take the median recovery time into account, and engineers judge how steady quality is by the standard deviation.
Take the first 20 words on any page of a book, write down the number of letters in each, and find the mean, mode and median. Discuss which measure describes a “typical” word length best.
“My scores”: write down your mathematics marks this term (or the results of 10 short tests). Find the mean, mode, median and range, then compute the standard deviation with a table of squared deviations. Which measure describes your results best?