A trimean is a number that represents the general tendency of a set of numbers or data set. Like the mean, median, and mode, it is a measure of central tendency. It is defined to be the weighted average of the median and upper and lower quartiles. What that means is that:

**Trimean=(Q _{1}+2Q_{2}+Q_{3})/4 **

where Q_{1} And Q_{3} are the upper and lower quartiles (also known as hinges) and Q_{2} is the mean.

The two quartiles in the formula make the trimean **more likely to be representative of the data** than the median. The formula’s weighted middle results in a lower sensitivity to outliers.

## Example

Let’s say you wanted to find the trimean for the set 1, 2, 3, 4, 5, 6, 7.

Your median is 4, Q1 is 2 and Q3 is 6, so your trimean will be:

(4 · 2 + 2 + 6) / 4, or 16 / 4 = 4.

The data was uniformly spaced and symmetric, so the median and trimean are equal.

This is not always the case, however. For example, take the set 1, 3, 5, 6, 7, 9, 12, 15, 18, 19, 90.

The median is digit 6 — the number 9.

Q_{1} is 5 and Q_{3} is 18, so your trimean is (9 · 2 + 5 + 18) / 4 = 41 / 4 = 10.25. This is different from the median (9).

The set 1, 2, 3, 15, 1000, 2000, 3000 will have a trimean of (30+2+2000)/4, or 508.

## Why Use the Trimean

The trimean is easy to calculate, and a surprisingly good estimate of the arithmetical mean. It is considered ‘resistant’ or ‘robust’ because it is not very effected by outliers. The inclusion of the weighted median give it a strong emphasis on the center, but the two quartiles also bring in significant representation from the edges. Maybe that’s why the Trimean has been also named the BES (Best Easy Systematic) Estimate.

## Sources

What is a Statistical Trimean

Wolfram: Trimean

CRC Concise Encyclopedia of Mathematics

Measures of Central Tendency

Central Tendency and Variability, Issue 83

If you prefer an online interactive environment to learn R and statistics, this *free R Tutorial by Datacamp* is a great way to get started. If you're are somewhat comfortable with R and are interested in going deeper into Statistics, try *this Statistics with R track*.

*Facebook page*and I'll do my best to help!