What is Mean Absolute Deviation (MAD)?

The Mean Absolute Deviation (MAD) is a critical statistic used to quantify the dispersion or variability of a dataset. Specifically, it represents the average of the absolute distances between each data point and the dataset's arithmetic mean. Unlike measures such as variance or standard deviation, MAD does not square the differences. This feature makes it highly intuitive and less sensitive to extreme outliers, offering a balanced view of real-world consistency.

The Mathematical Equations Behind Mean Absolute Deviation

Calculating the Mean Absolute Deviation is an iterative two-step process. First, we compute the dataset's average (mean), and then we compute the average of the absolute deviations from that mean.

Step 1: Compute the Arithmetic Mean ($\bar{x}$)

$\bar{x} = \frac{\sum_{i=1}^{n} x_i}{n}$

Step 2: Compute the Mean Absolute Deviation (MAD)

$MAD = \frac{\sum_{i=1}^{n} |x_i - \bar{x}|}{n}$

Where:

• $x_i$ represents each individual value in your sample set.
• $\bar{x}$ represents the calculated arithmetic mean of the dataset.
• $n$ is the total number of data points (sample size).
• $|x_i - \bar{x}|$ represents the absolute difference (always positive) between each value and the mean.

Step-by-Step Example Calculation

To illustrate how Mean Absolute Deviation is calculated manually, let us evaluate the dataset: 10, 15, 12, 18, 20, 22 ($n = 6$).

1. Calculate the Mean ($\bar{x}$): Sum the numbers and divide by $6$:
   $\bar{x} = \frac{10 + 15 + 12 + 18 + 20 + 22}{6} = \frac{97}{6} \approx 16.1667$
2. Find the Absolute Deviations ($|x_i - \bar{x}|$):
   • $|10 - 16.1667| = 6.1667$
   • $|15 - 16.1667| = 1.1667$
   • $|12 - 16.1667| = 4.1667$
   • $|18 - 16.1667| = 1.8333$
   • $|20 - 16.1667| = 3.8333$
   • $|22 - 16.1667| = 5.8333$
3. Sum the Absolute Deviations:
   $6.1667 + 1.1667 + 4.1667 + 1.8333 + 3.8333 + 5.8333 = 23.0000$
4. Divide by the Sample Size ($n = 6$):
   $MAD = \frac{23.0000}{6} \approx 3.8333$

Comparing Measures of Dispersion

In statistics, variance, standard deviation, and MAD are often used to achieve similar objectives. However, they handle dispersion differently:

Why is MAD Important in Business Operations?

In supply chain operations, logistics, and retail business administration, MAD is the preferred metric for calculating **Forecast Error**. A low MAD indicates that your forecasting model matches actual customer demand perfectly, while a high MAD signifies substantial forecasting inaccuracies. Analyzing MAD allows organizations to adjust safety stock thresholds, avoid costly inventory stockouts, and manage warehousing pipelines with high efficiency.