Direct Answer
Average deviation, also called mean absolute deviation, is the mean of the absolute distances of values from their mean. It measures dispersion in the data's own units and is less sensitive to outliers than standard deviation. A larger value means observations sit further from their average.
Average Deviation: Formula, Meaning, Signals, Examples and How to Use It
How Is Average Deviation Calculated?
Average deviation, also called mean absolute deviation, is the mean of the absolute distances of values from their mean. It measures dispersion in the data's own units and is less sensitive to outliers than standard deviation.
Formula: AD = (1 / n) x sum of |x_i - mean|
Inputs:
- A series of values such as closing prices or returns
- Window length n
Worked example. The values 10, 12, 14 and 16 have a mean of 13 and an average deviation of 2.00. The inputs are illustrative numbers, not market data.
Reading it. A larger value means observations sit further from their average. For roughly normally distributed data it is about 0.8 of the standard deviation, so the two move together but are not equal.
Limits. Some tools use the median instead of the mean as the center, so check the definition. It shares the weakness of any window statistic: it depends on window length and says nothing about the order of observations.
What is Average Deviation?
Average deviation, also called mean absolute deviation, is the mean of the absolute distances of values from their mean. It measures dispersion in the data's own units and is less sensitive to outliers than standard deviation.
How to use Average Deviation
A larger value means observations sit further from their average. For roughly normally distributed data it is about 0.8 of the standard deviation, so the two move together but are not equal. A reading alone is never a buy or sell signal; it needs context from price structure, volume, volatility and the broader market regime.
Strengths
- Using absolute rather than squared distances gives each observation influence in proportion to its size, so outliers weigh less than under variance.
- The result is in the data's own units, so a value of 1.5 means observations sit about 1.5 units from the mean on average.
- Reproducible when the formula and data convention are fixed.
Weaknesses and limitations
- The absolute value function has no smooth derivative at zero, so it is less convenient than variance in statistical models and formulas.
- For normally distributed data it is about 80 percent of the standard deviation, so the two cannot be swapped without rescaling.
- Correlated indicators can create false confidence by repeating the same underlying information.
Editorial and risk note
This page is educational content, not individualized investment advice. It should not imply guaranteed prediction, accuracy or outperformance.
Frequently Asked Questions
Is Average Deviation a buy or sell signal?
No. A larger value means observations sit further from their average. Some tools use the median instead of the mean as the center, so check the definition. A trade built on it still needs a trigger, an invalidation rule, a position size and realistic execution assumptions.
What is the best setting for Average Deviation?
Average Deviation takes these inputs: a series of values such as closing prices or returns; window length n. There is no universal best setting for the tunable ones, so test them across instruments, regimes and out-of-sample periods and favor stable parameter regions over one historical winner.
Can Average Deviation be used by itself?
Some tools use the median instead of the mean as the center, so check the definition. It shares the weakness of any window statistic: it depends on window length and says nothing about the order of observations. For that reason it is read next to measures of direction, participation, valuation, liquidity and risk, not alone.
Does Average Deviation work on every timeframe?
The calculation (AD = (1 / n) x sum of |x_i - mean|) can be run on any bar size, but behavior is not portable: a reading on a five-minute chart describes a very different market window from the same reading on a daily chart. Validate the exact timeframe before relying on it.
Why does Average Deviation give false signals?
The absolute value function has no smooth derivative at zero, so it is less convenient than variance in statistical models and formulas. For normally distributed data it is about 80 percent of the standard deviation, so the two cannot be swapped without rescaling. Lag, noise and regime changes add to this, because market participants react to new information after the reading is calculated.
How should Average Deviation be backtested?
Rebuild Average Deviation from a series of values such as closing prices or returns using point-in-time data, write the rules before testing, include delisted securities where relevant, model realistic fills and costs, reserve a validation sample and compare with a simpler baseline.