Box Plot (Box-and-Whisker Plot)

A visual tool that displays the distribution of data through quartiles, making it easy to identify outliers and assess the symmetry of your dataset.

Plot Overview & Components

What it shows:

Five key statistics of your data: minimum, first quartile (Q1), median (Q2), third quartile (Q3), and maximum, along with any outliers.

Components:

• • Box: Contains 50% of the data (Q1 to Q3)
• • Median line: Middle value dividing the data in half
• • Whiskers: Extend to min/max within 1.5×IQR
• • Outliers: Points beyond the whiskers

Advantages:

• • Quick visual assessment
• • Excellent outlier detection
• • Shows data distribution shape
• • Easy to compare multiple groups

Limitations:

• • Hides detailed distribution shape
• • Can miss bimodal distributions
• • Less precise than statistical tests
• • Subjective interpretation of symmetry

Quartiles & Fence Formulas

Quartiles split the sorted data into four equal parts. The platform uses the linear-interpolation percentile method, the same convention used by most statistical software.

Interquartile range

= 25th percentile (first quartile)

= 75th percentile (third quartile)

Whisker fences (outlier boundaries)

IQR

= interquartile range, Q3-Q1

Points beyond the fences are flagged as outliers; whiskers extend to the most extreme data point still inside the fences.

Key Assumptions

• • Data are continuous and measured on an interval or ratio scale
• • Quartiles are computed on sorted (ranked) data, so order matters, not distribution shape
• • The 1.5×IQR fence is a convention, not a statistical test — it flags candidate outliers for review
• • At least ~10 observations are recommended before quartile estimates are considered stable

Reading the Box Plot

Interpretation Guidelines & Best Practices

Implementation on sixsigmacenter.com

Interpreting Box Plot Patterns

Example Data Layout for Box Plot Analysis

Single column of continuous data for box plot analysis. Visual assessment of distribution shape, outliers, and symmetry. Sample Size Recommendation: Minimum 20 observations for reliable quartile estimates, preferably 50+ for stable outlier detection and accurate distribution shape assessment.

This is how your spreadsheet or CSV file should be structured before you upload it. Match the column names, keep one row per observation, and leave the analysis to the platform.