Mean Absolute Deviation vs Standard Deviation
Master the key differences between MAD and SD for better statistical analysis and trading decisions
Understanding Variability Measures
Why Measure Variability?
Variability measures help us understand how spread out data points are from the central tendency. Both MAD and Standard Deviation serve this purpose but use different mathematical approaches with distinct advantages.
Trading Applications
In trading, understanding variability helps assess risk, set stop losses, and identify market volatility patterns. Each measure provides unique insights for different trading strategies.
Key Learning Objective
By the end of this lesson, you'll understand when to use MAD versus Standard Deviation, their computational differences, and practical applications in financial analysis.
Definitions and Formulas
Mean Absolute Deviation
Average of Absolute Differences
Definition
The Mean Absolute Deviation measures the average absolute difference between each data point and the mean of the dataset. It provides a straightforward measure of variability that's easy to interpret.
Formula
Where:
xi = individual data points
x̄ = mean of the dataset
n = number of data points
|...| = absolute value
Key Characteristics
- ✓ Easy to understand and calculate
- ✓ Less sensitive to outliers
- ✓ Uses same units as original data
- ✓ Robust measure of variability
Standard Deviation
Square Root of Variance
Definition
Standard Deviation measures the square root of the average squared differences from the mean. It's the most commonly used measure of variability in statistics and finance.
Formula
Where:
xi = individual data points
x̄ = mean of the dataset
n = number of data points
√ = square root
Key Characteristics
- ✓ Widely used in statistical analysis
- ✓ More sensitive to outliers
- ✓ Foundation for many statistical tests
- ✓ Normal distribution properties
Interactive Comparison
Visualization: MAD vs Standard Deviation
When to Use MAD
Data with Outliers
MAD is less affected by extreme values, making it ideal for skewed distributions.
Simple Interpretation
Easy to explain to non-technical stakeholders - "average distance from mean".
Robust Analysis
When you need a measure that's not heavily influenced by extreme observations.
When to Use Standard Deviation
Normal Distributions
Perfect for data following normal distribution patterns with 68-95-99.7 rule.
Statistical Testing
Required for most statistical tests, confidence intervals, and hypothesis testing.
Financial Modeling
Standard in finance for risk measures, portfolio theory, and volatility analysis.
Practical Examples
Example 1: Stock Price Analysis
Sample Data: Daily Stock Prices
$102, $98, $105, $101, $99, $103, $100, $96, $104, $97
Mean: $100.50
MAD Calculation:
Average absolute deviation from mean = $2.50
Standard Deviation Calculation:
Square root of variance = $3.03
Interpretation
MAD ($2.50) indicates the average distance of prices from the mean, showing moderate variability. Standard Deviation ($3.03) is higher due to squaring deviations, emphasizing larger deviations more. For this stock, MAD suggests a more stable view of volatility, while SD highlights potential extreme movements.
Insight: Use MAD for robust risk assessment in volatile markets; use SD for precise volatility modeling.
Example 2: Portfolio Returns
Sample Data: Monthly Returns (%)
2.5, -1.0, 3.0, 0.5, -0.5, 4.0, 1.5, -2.0, 20.0, 0.0
Mean: 2.80%
MAD Calculation:
Average absolute deviation from mean = 3.80%
Standard Deviation Calculation:
Square root of variance = 6.12%
Interpretation
The outlier (20%) significantly impacts SD (6.12%), making it much higher than MAD (3.80%). MAD provides a more robust measure, ignoring the outlier's exaggerated effect, while SD reflects the full range of variability, useful for risk models like VaR.
Insight: MAD is better for portfolios with occasional extreme returns; SD is ideal for standardized risk metrics.
Applications in Trading
Volatility Assessment
Use SD for Bollinger Bands or volatility indicators; use MAD for robust volatility measures in markets with outliers.
Risk Management
SD is key for Value at Risk (VaR) models; MAD helps set stop losses in strategies sensitive to extreme price moves.
Portfolio Diversification
SD informs correlation and portfolio variance; MAD offers a simpler metric for assessing return consistency.
Pro Tip
Combine MAD and SD in your analysis: use MAD for initial robustness checks and SD for standardized financial models.
Tools to Get Started
Interactive Volatility Chart
Example of MAD and SD applied to daily stock returns over 30 days.