• Foundation
  • About 14 min
  • 5 practice questions

Mean, median and mode together: skewness and the empirical relation

Read the shape of data from the order of mean, median and mode, use the empirical relation mode ≈ 3 median − 2 mean, and measure skewness with (mean − mode)/standard deviation.

If something looks wrong, please tell us.

The three averages answer different questions, and the gaps between them tell you about the shape of the data. When the mean, median and mode are equal, the data are balanced. When one long tail pulls the mean away from the others, the data are skewed. This lesson reads those signs and uses a rule that links the three averages.

Symmetric and skewed data

ShapeDescriptionOrder of the averages
Symmetricbalanced on both sidesmean = median = mode
Positively skewed (right tail)a few very large valuesmean > median > mode
Negatively skewed (left tail)a few very small valuesmean < median < mode

The mean is pulled most strongly by extreme values, the median less, and the mode least. In a right-skewed set such as incomes or house prices, a few very large values raise the mean above the median, which is why the median is often quoted instead.

The empirical relation

For moderately skewed data, the three averages are roughly related by mode ≈ 3 × median − 2 × mean. This is an approximation, not an exact law, but it is widely used to estimate one average from the other two. Rearranged, median ≈ (mode + 2 × mean)/3.

Mode ≈ 3 median − 2 mean. In right-skewed data mean > median > mode; in left-skewed data the order reverses. Pearson's measure of skewness: (mean − mode)/σ — positive for a right tail, negative for a left tail, zero for symmetric data.

Worked example 1: estimating the mode

A data set has mean 24 and median 22. Then mode ≈ 3 × 22 − 2 × 24 = 66 − 48 = 18. The order mean (24) > median (22) > mode (18) shows a right-skewed set.

Worked example 2: estimating the median

A set has mean 40 and mode 25. Then median ≈ (25 + 2 × 40)/3 = 105/3 = 35. Again mean > median > mode, a right-skewed set.

Worked example 3: a measure of skewness

Karl Pearson's coefficient of skewness is (mean − mode)/σ, where σ is the standard deviation. If the mean is 24, the mode is 18 and σ = 6, then the coefficient is (24 − 18)/6 = 1. A positive value means a right tail; the larger the value, the greater the skew. Using the empirical relation, mean − mode = 3(mean − median), so the same number is 3(24 − 22)/6 = 1, which agrees.

Worked example 4: one extreme value

Consider the marks 2, 3, 3, 4, 4, 4, 5, 5, 6, 20. The sum is 56 and n = 10, so the mean is 5.6. In order, the 5th and 6th values are both 4, so the median is 4. The mode is 4, since 4 occurs three times. The single value 20 pulls the mean above the median and mode: mean 5.6 > median 4 = mode 4. Without the 20, the other nine marks have mean 36/9 = 4, equal to the median and mode.

Which average should be quoted?

  • Symmetric data with no extreme values: the mean, which uses every value.
  • Skewed data or data with outliers: the median, which resists extreme values.
  • Categories or the most common size: the mode.

Common mistakes

  • Using the empirical relation as if it were exact: it is only an approximation.
  • Reversing the order of the averages: a right tail raises the mean the most.
  • Forgetting the sign of the skewness coefficient: (mean − mode) is negative for a left tail.
  • Calling data symmetric because the mean and median are close, without checking the mode.

Key takeaways: the order of mean, median and mode shows the skew. The empirical relation mode ≈ 3 median − 2 mean links them. One extreme value moves the mean much more than the median or mode.

Check your understanding

  1. 1. A data set has mean 24 and median 22. Using the empirical relation, what is the approximate mode?

    1. 20
    2. 26
    3. 18
    4. 22
    Show answer

    Answer: C. Mode ≈ 3 × median − 2 × mean = 66 − 48 = 18.

  2. 2. A data set has mean 40 and mode 25. Using the empirical relation, what is the approximate median?

    1. 35
    2. 32.5
    3. 30
    4. 37.5
    Show answer

    Answer: A. Median ≈ (mode + 2 × mean)/3 = (25 + 80)/3 = 35.

  3. 3. In a positively skewed (right-tailed) distribution, the usual order is

    1. mode > median > mean
    2. median > mean > mode
    3. mean = median = mode
    4. mean > median > mode
    Show answer

    Answer: D. A long right tail pulls the mean up most, the median a little, and leaves the mode at the peak. So mean > median > mode.

  4. 4. The mean is 24, the mode is 18 and the standard deviation is 6. What is Pearson's coefficient of skewness (mean − mode)/σ?

    1. −1
    2. 1
    3. 6
    4. 1/6
    Show answer

    Answer: B. (24 − 18)/6 = 1. The positive sign indicates a right tail.

  5. 5. What is the mean of 2, 3, 3, 4, 4, 4, 5, 5, 6, 20?

    1. 5.6
    2. 4
    3. 5
    4. 6.5
    Show answer

    Answer: A. The sum is 56 and there are 10 values, so the mean is 5.6. (The median and mode are both 4.)

Privacy · Terms · Refunds · Delivery