Mean Deviation Calculator

Mean Deviation Calculator

Emerging AI Skill PRO

Enter Calculation

Formula

MAD=1n∑i=1n|xi−x‾|xi∈Data Set\text{MAD} = \frac{1}{n}\sum_{i=1}^{n}\left| x_i - \bar{x} \right| \qquad x_i \in \text{Data Set}
Usage stats

Advertisement

Results

Mean Absolute Deviation
2.4
Property Value
Number of Values 5
Mean 14
Median 14
Mean Absolute Deviation 2.4

Report an error on this page

What Is the Mean Deviation Calculator?

The Mean Deviation Calculator computes the average distance between each value in your dataset and a central reference point — either the mean (average) or the median. This single number, known as the absolute deviation, tells you how spread out or consistent your data is. Unlike standard deviation, which squares differences, mean and median absolute deviation use plain absolute values, making them easier to interpret and less sensitive to extreme outliers. This tool works for any numeric data and is not specific to any country or currency.

How to Use It

  • Type your numbers separated by commas, for example: 4, 8, 6, 5, 12, 7.
  • Choose whether to measure deviation from the mean or the median.
  • Read the result instantly — the calculator returns the average absolute deviation along with the central value it used.

The Formula Explained

Mean Absolute Deviation (MAD) measures the average of the absolute differences between each data point and a central value:

$$\text{MAD} = \frac{1}{n}\sum_{i=1}^{n}\left| x_i - c \right|$$

Where \(x_i\) is each value, \(c\) is the chosen center (mean or median), and \(n\) is the number of data points. The bars indicate absolute value, so negative and positive differences are treated the same. Choosing the median as the center generally produces a smaller, more robust deviation when your data contains outliers.

Advertisement
Number line showing data points, the mean, and absolute distances from each point to the mean
Mean absolute deviation is the average of the distances from each data point to the mean.

Worked Example

Consider the dataset: 4, 8, 6, 5, 12, 7. The mean is \((4+8+6+5+12+7) \div 6 = 42 \div 6 = 7\). The absolute differences from 7 are: 3, 1, 1, 2, 5, 0. Their sum is 12, so the Mean Absolute Deviation $$\text{MAD} = 12 \div 6 = \mathbf{2.0}$$ This means values typically sit about 2 units away from the average.

Step diagram of computing absolute deviations from the mean and averaging them
Each value's distance from the mean is taken as a positive amount, then averaged.

Mean vs Median Absolute Deviation: Scenario Comparison

"Median-centered (average)" is the average of \(|x_i - \text{median}|\); "median-centered (median)" is the median of those deviations.

Dataset Mean Median Mean-centered MAD Median-centered (average) Median-centered (median) Note
Symmetric: 1, 2, 3, 4, 5 3 3 1.2 1.2 1 Mean and median coincide, so either average-based measure is representative.
Skewed: 1, 2, 2, 3, 10 3.6 2 2.56 2 1 The tail pulls the mean up; median-centered measures describe the typical point better.
Outlier: 10, 11, 12, 13, 100 29.2 12 28.32 18.4 1 Mean-centered value is dominated by the outlier; the median of deviations is most representative of the bulk.
Identical: 5, 5, 5, 5 5 5 0 0 0 No variability; all measures are zero.

Check for the outlier row: mean \(= 146/5 = 29.2\); deviations from the mean sum to 141.6, and \(141.6/5 = 28.32\). Deviations from the median 12 are 2, 1, 0, 1, 88 (sum 92), and \(92/5 = 18.4\); their median is 1.

Advertisement

Interpreting Your MAD Result

  • Same units as the data. If your data are in kilograms, the MAD is in kilograms. Only compare MAD values between datasets measured in the same units.
  • Larger means more spread. A MAD of 0 means every value is identical; the bigger it is, the further values typically sit from the center.
  • Judge it relative to scale. A MAD of 5 is large for data centered near 10 but small for data centered near 10,000. Dividing by the mean (\(\text{MAD}/\bar{x}\)) gives a unitless relative measure, provided the mean is not close to zero.
  • Link to standard deviation. For roughly normal data, the standard deviation is about 1.25 times the mean absolute deviation: $$\sigma \approx 1.2533 \times \text{MAD}$$ This relationship does not hold well for skewed or heavy-tailed data. The median of absolute deviations is usually scaled by about 1.4826 to estimate \(\sigma\) for normal data.
  • Small samples. With only a handful of points, MAD can change a lot when a single value is added or removed, so treat it as a rough description rather than a precise estimate.
  • Outliers. Mean-centered MAD is affected by extreme values, both through the deviations and through the mean itself. Median-based versions, especially the median of absolute deviations, are much less affected. Always state which variant you computed.

Conventions and edge cases

Each case below was run through this calculator; the result column is what it actually returns.

CaseInputResult
Decimals 0.1, 0.2, 0.30.1, 0.2, 0.30.0667
Even number of values (1, 2, 3, 4)1, 2, 3, 41
Negative values (−3, −1, 4)-3, -1, 42.6667
A zero in the list (0, 4, 9)0, 4, 93.1111
Sample or population (2, 4, 4, 4, 5, 5, 7, 9)2, 4, 4, 4, 5, 5, 7, 91.5
A single value70

Checked on 2026-11-08

Frequently Asked Questions

What is the difference between mean and median absolute deviation? Mean absolute deviation centers on the average, while median absolute deviation centers on the median. The median version is more resistant to extreme values and skewed data.

How does MAD differ from standard deviation? Standard deviation squares the differences and then takes a square root, which exaggerates large gaps. MAD uses raw absolute distances, so it is easier to explain and less affected by outliers.

Can MAD be zero? Yes. If every value in your dataset is identical, there is no variability, so the mean deviation equals zero.

Last updated:

Most popular in Math and Statistics

View all Math and Statistics calculators