Pearson’s Coefficient of Skewness Calculator

Use this unified calculator to find Pearson’s coefficient of skewness (also called Karl Pearson’s skewness) for both ungrouped (raw) data and grouped (frequency distribution) data. Measure distribution asymmetry using mean, median, and standard deviation.

Quick Start

Choose your data type, enter your values, and click Calculate:

Pearson's Coefficient of Skewness Calculator
Data Type Ungrouped (Raw Data) Grouped (Frequency Distribution)
Enter the X Values (Separated by comma,)
Type of Frequency Distribution DiscreteContinuous
Enter the Classes for X (Separated by comma,)
Enter the frequencies (f) (Separated by comma,)
Results
Number of Observations (N):
Ascending order of X values:
Sample Mean:
Sample Median:
Sample Std. Deviation:
Pearson's Coefficient of Skewness:

Understanding Pearson’s Coefficient of Skewness

Pearson’s coefficient (also called Karl Pearson’s skewness) is the most commonly used skewness measure because:

  • ✅ Uses all data points (mean and SD incorporate all values)
  • ✅ Easier to interpret than moment coefficient
  • ✅ Ranges from approximately -3 to +3
  • ✅ Well-established in statistical practice
  • ✅ Less sensitive to outliers than moment coefficient

The Relationship Between Mean and Median

Pearson’s coefficient reveals the relationship between mean and median:

  • Symmetric: Mean ≈ Median → Sk ≈ 0
  • Right-skewed: Mean > Median → Sk > 0
  • Left-skewed: Mean < Median → Sk < 0

Interpretation Scale

Pearson’s Coefficient Distribution Interpretation
-1 to -0.5 Left-skewed Moderate negative skewness
-0.5 to 0 Slightly left-skewed Mild negative skewness
-0.5 to 0.5 Approximately symmetric Very mild or no skewness
0 to 0.5 Slightly right-skewed Mild positive skewness
0.5 to 1 Right-skewed Moderate positive skewness
> ±1 Highly skewed Strong asymmetry

How to Use This Calculator

For Ungrouped (Raw) Data

Step 1: Select “Ungrouped (Raw Data)” as your data type

Step 2: Enter your data values separated by commas (e.g., 10, 15, 20, 25, 30)

Step 3: Click “Calculate”

Results will show:

  • Number of observations (N)
  • Sorted values
  • Sample mean
  • Sample median
  • Sample standard deviation
  • Pearson’s coefficient of skewness

For Grouped (Frequency Distribution) Data

Step 1: Select “Grouped (Frequency Distribution)” as your data type

Step 2: Choose distribution type (Discrete or Continuous)

Step 3: Enter classes and frequencies

Step 4: Click “Calculate”

Results will show:

  • All calculated values above

Formula

Pearson’s Coefficient of Skewness

$$S_k = \frac{3(\overline{x} - M)}{s_x}$$

Where:

  • $\overline{x}$ = Sample mean
  • $M$ = Median
  • $s_x$ = Sample standard deviation

Why Multiply by 3?

The factor of 3 is empirical and comes from Karl Pearson’s research. For many distributions, the relationship:

$$\text{Mean} - \text{Mode} \approx 3(\text{Mean} - \text{Median})$$

holds approximately, so Pearson standardized the formula using this factor.

Alternative Form

Some texts use:

$$S_k = \frac{\overline{x} - M_o}{s_x}$$

Where $M_o$ is the mode. This form is less common because mode is harder to define and less stable than median.


Why Pearson’s Coefficient?

Advantages:

  • ✅ Uses all data (mean and SD consider every value)
  • ✅ Most commonly reported in practice
  • ✅ Stable and well-defined measure
  • ✅ Easy to interpret and compare
  • ✅ Suitable for all distribution shapes

Disadvantages:

  • ❌ More affected by outliers than Bowley’s or Kelly’s
  • ❌ Can be affected by extreme values
  • ❌ May be misleading for multimodal distributions

Worked Examples

Example 1: Ungrouped Data - Symmetric Distribution

Data: Scores: 20, 30, 40, 50, 60, 70, 80

Find Pearson’s coefficient of skewness.

Solution:

Step 1: Calculate Mean

$$\overline{x} = \frac{20+30+40+50+60+70+80}{7} = \frac{350}{7} = 50$$

Step 2: Find Median

With N = 7 (odd), median is the 4th value = 50

Step 3: Calculate Standard Deviation

Sum of squares = 400+900+1600+2500+3600+4900+6400 = 20,300

$$s_x = \sqrt{\frac{20300 - \frac{350^2}{7}}{6}} = \sqrt{\frac{20300 - 17500}{6}} = \sqrt{\frac{2800}{6}} = \sqrt{466.67} = 21.6$$

Step 4: Calculate Pearson’s coefficient

$$S_k = \frac{3(50-50)}{21.6} = \frac{0}{21.6} = 0$$

Answer: Sk = 0

Interpretation: Distribution is perfectly symmetric; no skewness present.


Example 2: Ungrouped Data - Right-Skewed Distribution

Data: Income (thousands): 20, 25, 30, 35, 40, 45, 100

Find Pearson’s coefficient of skewness.

Solution:

Step 1: Calculate Mean

$$\overline{x} = \frac{20+25+30+35+40+45+100}{7} = \frac{295}{7} = 42.14$$

Step 2: Find Median

With N = 7, median is 4th value = 35

Step 3: Calculate Standard Deviation

Sum of X² = 400+625+900+1225+1600+2025+10000 = 16,775

$$s_x = \sqrt{\frac{16775 - \frac{295^2}{7}}{6}} = \sqrt{\frac{16775 - 12433}{6}} = \sqrt{721.33} = 26.86$$

Step 4: Calculate Pearson’s coefficient

$$S_k = \frac{3(42.14-35)}{26.86} = \frac{3(7.14)}{26.86} = \frac{21.42}{26.86} = 0.797$$

Answer: Sk ≈ 0.797

Interpretation: Strong right skewness; the distribution has a pronounced tail toward higher values (the outlier 100). Mean > Median indicates rightward asymmetry.


Example 3: Grouped Data (Discrete) - Test Scores

Problem: Grade distribution for 50 students. Find Pearson’s coefficient of skewness.

Grade 2 3 4 5 6
Frequency 3 8 20 15 4

Solution:

Step 1: Calculate Mean

Grade Frequency f×x
2 3 6
3 8 24
4 20 80
5 15 75
6 4 24
Total 50 209

$$\overline{x} = \frac{209}{50} = 4.18$$

Step 2: Find Median

Cumulative frequencies: 3, 11, 31, 46, 50

  • N/2 = 25
  • Cumulative ≥ 25 is at grade 4
  • Median = 4

Step 3: Calculate Standard Deviation

Grade f f×x²
2 3 12
3 8 72
4 20 320
5 15 375
6 4 144
Total 50 923

$$s_x = \sqrt{\frac{923 - \frac{209^2}{50}}{49}} = \sqrt{\frac{923 - 872.42}{49}} = \sqrt{\frac{50.58}{49}} = 1.016$$

Step 4: Calculate Pearson’s coefficient

$$S_k = \frac{3(4.18-4)}{1.016} = \frac{3(0.18)}{1.016} = \frac{0.54}{1.016} = 0.531$$

Answer: Sk ≈ 0.531

Interpretation: Moderate positive (right) skewness; the distribution leans slightly toward higher grades.


Example 4: Grouped Data (Continuous) - Age Distribution

Problem: Age distribution of 60 customers. Find Pearson’s coefficient of skewness.

Age Group 20-30 30-40 40-50 50-60 60-70
Frequency 5 15 20 15 5

Solution:

Step 1: Calculate Mean

Midpoint Frequency f×x f×x²
25 5 125 3,125
35 15 525 18,375
45 20 900 40,500
55 15 825 45,375
65 5 325 21,125
Total 60 2,700 128,500

$$\overline{x} = \frac{2700}{60} = 45$$

Step 2: Find Median

N/2 = 30

  • Cumulative frequencies: 5, 20, 40, 55, 60
  • Cumulative ≥ 30 is 40 (class 40-50)
  • Using median formula: M = 40 + ((30-20)/20)×10 = 40 + 5 = 45

Step 3: Calculate Standard Deviation

$$s_x = \sqrt{\frac{128500 - \frac{2700^2}{60}}{59}} = \sqrt{\frac{128500 - 121500}{59}} = \sqrt{\frac{7000}{59}} = \sqrt{118.64} = 10.89$$

Step 4: Calculate Pearson’s coefficient

$$S_k = \frac{3(45-45)}{10.89} = \frac{0}{10.89} = 0$$

Answer: Sk = 0

Interpretation: Distribution is perfectly symmetric; mean equals median, indicating no skewness. The distribution is evenly balanced around the center.


Comparison: All Skewness Measures

Measure Formula Basis Range Data Sensitivity Use Case
Pearson’s Mean, Median, SD -3 to +3 All data Standard measure
Bowley’s Q₁, Q₂, Q₃ -1 to +1 Middle 50% Robust to outliers
Kelly’s D₁, D₅, D₉ -1 to +1 Outer 80% Tail behavior
Moment All deviations -2 to +2 All data Detailed analysis

When to Use Pearson’s Coefficient

Use when:

  • Standard, comparable measure is needed
  • Publishing results (most recognized measure)
  • Data is approximately normal or near-normal
  • Outliers are not extreme

Avoid when:

  • Data has severe outliers (use Bowley’s instead)
  • Only tail behavior matters (use Kelly’s instead)
  • Complete moment information is needed (use moment coefficient)

Key Differences: Ungrouped vs. Grouped Data

Aspect Ungrouped Data Grouped Data
Data Format Individual raw values Classes with frequencies
Mean Calc. Direct summation Weighted by frequencies
Median Finding Direct from sorted values Class-based formula
SD Calculation From individual values From class midpoints
Accuracy Exact from raw data Approximate from classes

Common Mistakes to Avoid

WRONG: Forgetting to multiply by 3 in the formula ✓ RIGHT: Always use Sk = 3(Mean - Median)/SD

WRONG: Using population formula (divide by N) for sample data ✓ RIGHT: Use n-1 in denominator for sample standard deviation

WRONG: Mixing Pearson with other skewness interpretations ✓ RIGHT: Remember Pearson’s range is roughly -3 to +3, while Bowley’s is -1 to +1

WRONG: Assuming Mean > Median always means right skew ✓ RIGHT: Check that Sk is positive; mathematically confirmed by formula


Practical Interpretation Examples

Financial Returns (Sk = 0.85)

  • Moderately right-skewed
  • Positive outliers (extreme gains) possible
  • Downside risk may be more frequent

Student Test Scores (Sk = -0.45)

  • Slightly left-skewed
  • Easier test; scores cluster at higher end
  • Negative outliers (very low scores) possible

Customer Ages (Sk ≈ 0)

  • Symmetric
  • Evenly distributed across age range
  • Mean and median are similar

Explore other skewness measures:

Related descriptive statistics:

Learn More: