Skewness and Kurtosis Formulas:
| From: | To: |
Skewness and Kurtosis are statistical measures that describe the shape of a probability distribution. Skewness measures the asymmetry of the distribution, while Kurtosis measures the "tailedness" or peakiness of the distribution relative to a normal distribution.
The calculator uses the central moments formulas:
Where:
Explanation: These formulas use central moments (moments about the mean) to calculate dimensionless measures of distribution shape. Skewness indicates symmetry, while Kurtosis indicates tail behavior.
Details: Skewness helps identify if data is symmetric (skewness ≈ 0), right-skewed (positive), or left-skewed (negative). Kurtosis helps identify if data has heavier tails (leptokurtic, kurtosis > 3), lighter tails (platykurtic, kurtosis < 3), or similar to normal distribution (mesokurtic, kurtosis ≈ 3).
Tips: Enter the third central moment (μ₃), fourth central moment (μ₄), and standard deviation (σ). All values must be valid (standard deviation > 0). The results are dimensionless measures.
Q1: What do positive and negative skewness values mean?
A: Positive skewness indicates a longer right tail (mean > median), negative skewness indicates a longer left tail (mean < median), and zero indicates symmetry.
Q2: How do I interpret kurtosis values?
A: Kurtosis > 3 indicates heavy tails (leptokurtic), < 3 indicates light tails (platykurtic), and ≈ 3 indicates normal tail behavior (mesokurtic).
Q3: What are central moments?
A: Central moments are moments calculated about the mean of the distribution. The third central moment measures asymmetry, while the fourth measures tail weight.
Q4: When should I use these measures?
A: Use skewness and kurtosis to assess normality assumptions, identify outliers, and understand distribution characteristics in statistical analysis and modeling.
Q5: Are there alternative formulas for skewness and kurtosis?
A: Yes, sample skewness and kurtosis formulas include bias corrections, but these formulas using central moments are the fundamental definitions.