On this concept: Formula

Not sure which lesson to do first? Find your level and get a plan →

Math · Statistics & Probability · Grade 6-8

Mean Absolute Deviation

Mean absolute deviation (MAD) is the average distance between each data value and the mean, using absolute values so distances don't cancel.

MAD=∑∣xi−xˉ∣n

Quick Answer

Mean absolute deviation (MAD) is the average distance between each data value and the mean, using absolute values so distances don't cancel. Use it to describe how spread out a small data set is, in the same units as the data. Find the mean, find how far each value is from it, then average those distances. A small MAD means the values huddle near the mean; a large MAD means they are scattered.

Why This Matters

Two classes can both average 75 on a test while one has every score between 70 and 80 and the other has scores from 40 to 100. The mean alone hides that difference; MAD measures it in plain units, such as 'typically 4 points from the mean'. It is also the stepping stone to standard deviation, which uses the same distances from the mean but squares them.

Intuitive Explanation

Five friends stand on a number line at 2, 4, 6, 8 and 10. Their mean position is 6. Measure how far each friend is from 6: 4 steps, 2, 0, 2 and 4. The friend at 2 is on the left and the friend at 10 is on the right, but both are 4 steps away. The average of these distances is 125=2.4, so a typical friend stands about 2.4 steps from the centre.

The absolute value is what makes this work. If you kept the signs (−4,−2,0,2,4), the left and right sides would cancel and the total would be 0. That happens for every data set, because the mean is exactly the balance point of the data. Distances ignore direction, so they add up instead of cancelling.

Compare 4, 5, 6, 7, 8 with 2, 4, 6, 8, 10: both have mean 6, but their MADs are 1.2 and 2.4, so the second set is twice as spread out. Range also measures spread, but it uses only the two end values and ignores the middle: 2, 6, 6, 6, 10 and 2, 2, 6, 10, 10 both have range 8, yet their MADs are 1.6 and 3.2.

Think of it like this. MAD is like the average walk from home to school for a class. Whether a student lives north or south of the school does not matter, only how far. Average everyone's walk and you know how spread out the neighbourhood is. One difference: in MAD the 'school' always stands exactly at the mean of the data.

Core idea. MAD is the mean of the absolute distances of each value from the data's mean.


When to Use

Use MAD when a question asks how spread out or consistent a data set is, or how far values typically sit from the mean, and the answer should be in the data's own units. It suits small data sets you can work by hand. If the problem squares the deviations, that is variance or standard deviation; if it only asks for the gap between the largest and smallest values, that is the range.

Tip. Ask: Am I averaging the ABSOLUTE distances of each value from the mean (not squared distances, not signed ones)?

How to Recognize It

Before computing a MAD, check what kind of spread the question asks about, what units the answer needs, and which mean the distances are measured from.

  1. Is the question about how spread out or consistent the values are, rather than about a typical value?

    If yes, you need a measure of spread such as MAD. If the question asks for the typical or middle value itself, use the mean, median or mode instead.

  2. Does the question want the spread in the same units as the data, such as points or minutes?

    If yes, MAD gives exactly that: a MAD of 3 minutes means values typically sit 3 minutes from the mean. Variance would give squared units, like square minutes, and is a step toward standard deviation.

  3. Does the question only care about the two most extreme values?

    If yes, the range, largest minus smallest, is enough. MAD uses every value, so one unusual value moves it far less than it moves the range.

  4. Are you comparing two groups whose means are different, such as two classes' quiz scores?

    If yes, find each group's own mean first and measure its distances from that, then compare the two MADs. The group with the smaller MAD is more consistent, even if its mean is lower.

Mean Absolute Deviation compared with Standard deviation, Variance, and Range

All four rows measure how spread out data are, so they look interchangeable. Ask how each one treats distance: the absolute distance from the mean (MAD), the squared distance (variance), the square root of that (standard deviation), or only the two extremes (range).

Mean Absolute Deviation

Meaning
Use this when you need a simple, same-units measure of how far typical values sit from the mean.
Key test
Am I averaging the ABSOLUTE distances of each value from the mean (not squared distances, not signed ones)?
Formula
MAD=∑∣xi−xˉ∣n
Example
Find the MAD of the data set 6, 8, 10, 12, 14.

Standard deviation

Meaning
Averages SQUARED deviations then square-roots, giving more weight to far-out points.
Key test
Use when you need the standard statistical spread measure for further analysis.
Formula
∑(xi−xˉ)2n
Example
Spread for a normal-curve calculation

Variance

Meaning
The mean of the squared deviations, in squared units, before the square root.
Key test
Use when you need spread in squared units or for variance formulas.
Formula
∑(xi−xˉ)2n
Example
Variance feeding into standard deviation

Range

Meaning
Just max minus min, ignoring all the middle values.
Key test
Use for a quick crude spread from the two extremes only.
Formula
max⁡−min⁡
Example
High 95, low 60, range 35

Formula & Notation

MAD=∑∣xi−xˉ∣n
MAD=1n∑i=1n∣xi−xˉ∣ where xˉ=1n∑i=1nxi

How to read it: ∣xi−xˉ∣ is the absolute deviation of value xi from the mean xˉ

Worked Examples

Example 1 — Spread of scores

Easy

Find the MAD of the data set 6, 8, 10, 12, 14.
Show the steps and the answer
  1. Find the mean: 6+8+10+12+145=505=10.

    MAD measures distance from the mean, so the centre comes first.

  2. Find each distance from 10: ∣6−10∣=4, ∣8−10∣=2, ∣10−10∣=0, ∣12−10∣=2, ∣14−10∣=4.

    6 is 4 below the mean and 14 is 4 above it; both count as a distance of 4.

  3. Average the distances: 4+2+0+2+45=125=2.4.

    Dividing by the 5 values gives the typical distance of one value from the mean.

Answer: MAD=2.4

Takeaway: Mean first, then distances without signs, then the average of those distances: a typical value here sits 2.4 units from 10.

Example 2 — Squaring instead

Standard

Same data 6, 8, 10, 12, 14, but you square each deviation and average: 16+4+0+4+165=8. Is 8 the MAD?
Show the steps and the answer
  1. Look at what was done to each deviation: 42=16, 22=4, 02=0, and so on.

    Squaring is the step that defines variance; MAD uses absolute values instead.

  2. Check the units: if the data are in points, 8 is in square points.

    A measure of spread in squared units cannot be compared directly with the data.

  3. Take the square root to get the standard deviation: 8≈2.83, a bit more than the MAD of 2.4.

    Squaring gives extra weight to the far values (the two 4s became 16s), so the standard deviation is usually larger than the MAD.

Answer: No — 8 is the variance; the MAD is 2.4

Takeaway: Absolute values give MAD; squares give variance, and its square root is the standard deviation.

Example 3 — Find the mistake: signed deviations

Application

For the data 3, 5, 7, 9, 16, Kim writes: "The mean is 8. The deviations are −5,−3,−1,1,8, so MAD=−5−3−1+1+85=05=0. The data have no spread." Find the mistake and correct it.
Show the steps and the answer
  1. Check Kim's mean and deviations: 3+5+7+9+165=405=8, and 3−8=−5, 5−8=−3, 7−8=−1, 9−8=1, 16−8=8.

    The arithmetic so far is correct; the error comes in the next step.

  2. Spot the error: Kim added signed deviations, and they total 0.

    Signed deviations from the mean add to 0 for every data set, so they can never measure spread.

  3. Use distances instead: 5,3,1,1,8, which add to 18.

    A value 5 below the mean is just as far away as a value 5 above it.

  4. Average: MAD=185=3.6.

    The values run from 3 to 16, so a spread of 0 could never be right; 3.6 is a sensible typical distance.

Answer: MAD=3.6

Takeaway: Take the absolute value of every deviation before averaging; signed deviations always cancel to 0.

Where You'll See It

  • Choosing a reliable basketball scorer

    Two players both average 15 points a game. One scores 13, 15, 17, 15, 15 (MAD 0.8); the other scores 5, 25, 10, 20, 15 (MAD 6). A coach who needs steady scoring picks the first player, even though their means are the same.

  • Filling cereal boxes at a factory

    A machine fills boxes labelled 500 g. Weights of 498, 503, 500, 499 and 500 g have mean 500 g and MAD 1.2 g. If the MAD rises to 8 g, many boxes are clearly under or over even though the average is still right, so the machine needs adjusting.

Common Mistakes

  1. The slip: Forgetting the absolute value

    Instead: signed deviations from the mean sum to zero, so you must take ∣xi−xˉ∣ first.

  2. The slip: Squaring the deviations

    Instead: that gives variance/standard deviation; MAD uses absolute value, not squares.

  3. The slip: Dividing by the wrong count

    Instead: divide the total absolute deviation by n, the number of data values.


Mini Practice

Try these on your own. Tap Reveal when you want to check.

  1. Find the mean absolute deviation of 2, 4, 6, 8.

    Hint: Find the mean, then the distance of each value from it.

  2. Find the MAD of 3, 5, 7, 9, 16.

    Hint: The mean is not the middle value here. Add the values first.

  3. Five daily high temperatures are 10, 12, 15, 11 and 12 °C. Find the MAD with units.

    Hint: Find the mean temperature first.

  4. Class A's quiz scores are 7, 8, 8, 9 and Class B's are 4, 6, 10, 12. Both means are 8. Find each MAD. Which class is more consistent?

    Hint: Smaller average distance from the mean means more consistent.

  5. You only want the gap between the highest and lowest test scores, 95 and 62. Do you need the MAD or the range?

    Hint: Does the question involve every value or just two of them?

  6. For 1, 3, 5, 7 (mean 4), Kim writes −3−1+1+34=0, so MAD =0. Correct Kim's work.

    Hint: Distances cannot be negative.

Want the full set?

50 practice questions for this concept — free to try, every one with a complete worked solution showing the why, not just the answer.

Frequently Asked Questions

Can the MAD ever be 0?

Yes, but only when every value is the same. If all five friends read 6 books, each distance from the mean is 0, so the MAD is 0: there is no spread at all. If even one value differs, at least one distance is above 0, and so is the MAD. It can never be negative, because a distance is never negative.

Why is MAD measured from the mean and not from the median?

Both versions exist. The one taught in middle school measures from the mean, so it pairs naturally with the mean as the center. Measuring absolute distances from the median also makes sense, and the median gives the smallest average distance of any center you could pick. For data with a few extreme values, the median version is often preferred, since outliers do not pull the median. Check which center a problem uses.

If two classes have the same mean score, how can MAD tell them apart?

Same mean, different spread. Class A scores 70, 75, 80, 85 and 90, and class B scores 50, 60, 80, 100 and 110. Both means are 80. Class A's distances are 10, 5, 0, 5 and 10, so its MAD is 6; class B's are 30, 20, 0, 20 and 30, so its MAD is 20. Class B's scores are much less consistent, even though the averages match.

Why do scientists usually use standard deviation instead of MAD?

Mostly because standard deviation works better with later math. Squared distances follow neat algebra rules, so standard deviations combine easily and fit the formula of the normal curve used in high school statistics. Absolute values are harder to handle in formulas. MAD is easier to understand and to compute by hand, which is why it comes first. For a normal distribution, the MAD is about 0.8 of the standard deviation.

Learning Path

← Before

MeanAbsolute Value
Mean Absolute Deviation

You are here

You need the Mean (the centre you measure from) and Absolute Value (distance without direction). MAD adds a single number for spread: the average distance from the mean. Next, Variance and Standard Deviation measure spread from the same deviations but square them, which gives extra weight to far-out values and is the standard measure in later statistics.

See Also