How to Find Mean Absolute Deviation- Calculation Steps and Examples
What Is Mean Absolute Deviation?
Mean Absolute Deviation (MAD) measures how spread out a set of numbers is from their average. Unlike variance or standard deviation, MAD gives you the average distance between each data point and the mean — in plain numbers you can actually interpret.
It's useful when you want to understand variability without dealing with squared or rooted values. No squaring. No square roots. Just absolute differences.
The Formula
Here's the MAD formula in its simplest form:
MAD = Σ|x - μ| / n
Where:
- Σ = sum of all values
- x = each individual data point
- μ = the mean (average) of all data points
- n = total number of data points
- |x - μ| = absolute value of each deviation from the mean
Step-by-Step Calculation
Step 1: Find the Mean
Add up all your data points and divide by how many there are.
Step 2: Calculate Each Deviation
Subtract the mean from each individual data point. This gives you positive or negative numbers.
Step 3: Take Absolute Values
Ignore whether each deviation is positive or negative. Drop the negative sign on any negative values. Every deviation becomes positive.
Step 4: Sum the Absolute Deviations
Add up all the absolute deviations.
Step 5: Divide by the Number of Data Points
Take that sum and divide by n. That's your MAD.
Example 1: Small Data Set
Test scores: 70, 85, 92, 78, 88
Step 1: Find the Mean
(70 + 85 + 92 + 78 + 88) ÷ 5 = 413 ÷ 5 = 82.6
Step 2: Calculate Deviations
| Score (x) | x - Mean (82.6) | |x - Mean| |
|---|---|---|
| 70 | 70 - 82.6 = -12.6 | 12.6 |
| 85 | 85 - 82.6 = 2.4 | 2.4 |
| 92 | 92 - 82.6 = 9.4 | 9.4 |
| 78 | 78 - 82.6 = -4.6 | 4.6 |
| 88 | 88 - 82.6 = 5.4 | 5.4 |
Step 3: Sum Absolute Deviations
12.6 + 2.4 + 9.4 + 4.6 + 5.4 = 34.4
Step 4: Divide by Number of Values
34.4 ÷ 5 = 6.88
These test scores have a MAD of 6.88. On average, each score sits 6.88 points away from the mean of 82.6.
Example 2: Real-World Scenario
Daily sales at a small store over a week: $320, $450, $380, $520, $410, $290, $470
Step 1: Find the Mean
(320 + 450 + 380 + 520 + 410 + 290 + 470) ÷ 7 = 2840 ÷ 7 = $405.71
Step 2 & 3: Calculate and Take Absolute Values
| Day | Sales | Deviation | |Deviation| |
|---|---|---|---|
| Mon | $320 | -85.71 | 85.71 |
| Tue | $450 | 44.29 | 44.29 |
| Wed | $380 | -25.71 | 25.71 |
| Thu | $520 | 114.29 | 114.29 |
| Fri | $410 | 4.29 | 4.29 |
| Sat | $290 | -115.71 | 115.71 |
| Sun | $470 | 64.29 | 64.29 |
Step 4: Sum and Divide
Sum of absolute deviations = 454.29
MAD = 454.29 ÷ 7 = $64.90
Daily sales deviate from the average by about $65. That's useful for forecasting — you know to expect swings of roughly $65 from your typical $406 daily revenue.
MAD vs. Standard Deviation
Both measure spread, but they work differently:
| Feature | Mean Absolute Deviation | Standard Deviation |
|---|---|---|
| Uses absolute values | Yes | No (uses squares) |
| Uses square roots | No | Yes |
| Interpretability | Direct (same units as data) | Less intuitive for non-statisticians |
| Outlier sensitivity | Moderate | High (squares amplify outliers) |
| Common use | Finance, forecasting, quality control | Research, academic statistics |
MAD is easier to explain to someone who doesn't work with stats. "On average, values are 6.8 units away from the mean" makes sense. Standard deviation doesn't give you that direct interpretation.
Common Mistakes to Avoid
- Forgetting the absolute value step. You must convert negative deviations to positive. Without this, your sum cancels out and gives you zero.
- Using the sample mean instead of population mean. If you're calculating MAD for an entire population, use the population mean. For a sample, use the sample mean. Mixing these up produces wrong results.
- Rounding too early. Keep decimals through the calculation. Only round at the final step.
- Confusing MAD with mean deviation. They're the same thing. Some textbooks call it "mean absolute deviation," others just call it "mean deviation."
Getting Started: How to Calculate MAD in Practice
Here's a quick process you can apply to any data set:
- Write down your data in a list or column
- Calculate the mean by summing all values and dividing by the count
- Subtract the mean from each value individually
- Convert each difference to its absolute value (remove any negative signs)
- Add all absolute deviations together
- Divide by the number of data points
You can do this with a basic calculator, spreadsheet software like Excel or Google Sheets, or by hand for small data sets. In spreadsheets, you'd use the formula: =SUM(ABS(A1:An - AVERAGE(A1:An))) / n
When to Use Mean Absolute Deviation
MAD works best when:
- You need a straightforward measure of variability
- Your audience needs to understand the spread in plain terms
- You're working with forecasts or demand planning
- You want to compare consistency across different data sets
- Outliers shouldn't dominate your spread measure
It's less appropriate when extreme values are the point of your analysis — in those cases, standard deviation or variance might serve you better since they weight outliers more heavily.