What Mean Deviation Is and Why You Calculate It
Mean deviation measures how far, on average, each number in a dataset sits from the middle value. It tells you the typical distance between individual data points and the mean — the larger the mean deviation, the more spread out your numbers are.
You use mean deviation when you want to know consistency. If you track your daily commute time over two weeks, mean deviation shows whether your trip takes roughly the same amount of time each day or varies wildly. A small mean deviation means your commute is predictable; a large one means it swings around.
Mean deviation differs from standard deviation (which squares the differences before averaging them). Mean deviation is simpler to calculate by hand and easier to interpret, because the result stays in the same units as your original data — if you measure in minutes, your mean deviation comes out in minutes.
Key Takeaways
- Mean deviation is the average distance between each data point and the mean of all data points.
- Calculate it by finding the mean, subtracting the mean from each number, taking the absolute value of each result, and averaging those absolute values.
- The formula is: Mean Deviation = (Σ|x − mean|) ÷ n, where n is the count of data points.
- Mean deviation always comes out as a positive number and uses the same units as your original data.
Step 1: Find the Mean of Your Data
Add all the numbers together and divide by how many numbers you have. This is the arithmetic mean — the starting point for everything that follows.
Example: You have five test scores: 72, 85, 78, 90, 80. Add them: 72 + 85 + 78 + 90 + 80 = 405. Divide by 5: 405 ÷ 5 = 81. Your mean is 81.
Write this number down. You will use it in the next step for every single data point.
Step 2: Subtract the Mean from Each Data Point
Take each number in your dataset and subtract the mean you just calculated. Some results will be negative (when the data point is below the mean) and some will be positive (when it is above the mean).
Using the test scores example with mean 81:
- 72 − 81 = −9
- 85 − 81 = 4
- 78 − 81 = −3
- 90 − 81 = 9
- 80 − 81 = −1
Keep all the negative signs. You will need them for the next step.
Step 3: Take the Absolute Value of Each Difference
Absolute value means you drop the negative sign and keep only the distance from zero. The symbol is two vertical bars: |−9| = 9. This step converts all your differences to positive numbers, because mean deviation measures distance, and distance is always positive.
Using the differences from Step 2:
- |−9| = 9
- |4| = 4
- |−3| = 3
- |9| = 9
- |−1| = 1
Now you have five positive numbers: 9, 4, 3, 9, 1.
Step 4: Add All the Absolute Values
Sum the numbers you got in Step 3. This total represents the combined distance of all data points from the mean.
9 + 4 + 3 + 9 + 1 = 26
Step 5: Divide by the Count of Data Points
Take the sum from Step 4 and divide it by how many numbers are in your dataset. This average distance is your mean deviation.
You have 5 test scores, so: 26 ÷ 5 = 5.2
Your mean deviation is 5.2. This means that, on average, each test score sits 5.2 points away from the mean of 81. One score was 72 (9 points below), another was 90 (9 points above), and the others clustered closer — so 5.2 points is the typical distance.
Working Through a Complete Example
Here is a full worked problem from start to finish. Suppose you record the number of customers who visit a small shop each day for one week: 42, 38, 45, 41, 39, 44, 40.
Step 1: Find the mean. (42 + 38 + 45 + 41 + 39 + 44 + 40) ÷ 7 = 289 ÷ 7 = 41.29 (rounded)
Step 2: Subtract the mean from each value. 42 − 41.29 = 0.71; 38 − 41.29 = −3.29; 45 − 41.29 = 3.71; 41 − 41.29 = −0.29; 39 − 41.29 = −2.29; 44 − 41.29 = 2.71; 40 − 41.29 = −1.29
Step 3: Take absolute values. 0.71, 3.29, 3.71, 0.29, 2.29, 2.71, 1.29
Step 4: Add them. 0.71 + 3.29 + 3.71 + 0.29 + 2.29 + 2.71 + 1.29 = 14.29
Step 5: Divide by count. 14.29 ÷ 7 = 2.04
The mean deviation is 2.04 customers. On a typical day, the shop's customer count varies by about 2 customers from the weekly average of 41.
Frequently Asked Questions
Why do I use absolute value instead of just keeping the negative signs?
If you kept the negative signs and added them all up, the negative and positive differences would cancel each other out, and you would always get zero. Absolute value forces you to measure distance only, which is what mean deviation is supposed to show.
Is mean deviation the same as standard deviation?
No. Mean deviation uses absolute values; standard deviation squares each difference before averaging. Standard deviation gives more weight to large differences and is more common in statistics software, but mean deviation is simpler to calculate by hand and easier to explain to someone unfamiliar with statistics.
What if all my data points are the same number?
The mean equals that number, every difference is zero, and the mean deviation is zero. A mean deviation of zero means there is no spread — all values are identical.
Can mean deviation be negative?
No. Because you take absolute values in Step 3, mean deviation is always zero or positive. A result of zero means no variation; any positive number means the data points spread around the mean.
Do I round the mean before I subtract it from each data point?
You can, but rounding introduces small errors that add up. It is more accurate to keep the full decimal value of the mean through all your subtractions, then round only your final answer if needed.