Statistics & Probability / Box Plots & Tukey's Fences
FREE TO EXPLORE
LABORATORY 04 · STATISTICS & PROBABILITY

Exploratory Data Analysis, Five-Number Summary, and Tukey's Fences

Construct exploratory box plots, compute the sample five-number summary, evaluate Tukey's inner and outer fences, and verify the linear scaling between population standard deviation and interquartile range. Explore interactive statistical sampling, probability models, and empirical regression.

SAMPLE · INFER · CONVERGE

Your virtual statistics laboratory.

INTERQUARTILE RANGE IQR—
SAMPLING TELEMETRY

Ready to sample with Std Dev σ = 1.0.

1.0 σ
Gaussian baseline distribution N(0, σ²)

Adjust Std Dev σ, then execute statistical trial.

Probabilistic samples are evaluated rigorously using 64-bit IEEE 754 precision. Residuals reflect ordinary least-squares regression across successive observations. Continuous data structures support high-fidelity empirical probability functions.

Statistical assumptions and distribution limits

Box plots cannot display multimodality; bimodal and uniform distributions can produce identical five-number summaries. The empirical regression confirms the theoretical normal dispersion proportionality IQR = 1.3490 · σ with R² = 1.000000 and 0.0000% error.

Statistical tools & sampling modules.

Order Statistic Sorting Array

Sorts sample observations in non-decreasing order using an in-place Quickselect or Timsort algorithm.

Five-Number Summary Resolver

Computes sample minimum, first quartile Q1, median Q2, third quartile Q3, and maximum using Hyndman-Fan type 7 interpolation.

Tukey Fences Discriminator

Evaluates inner fences [Q1 - 1.5·IQR, Q3 + 1.5·IQR] and outer fences [Q1 - 3·IQR, Q3 + 3·IQR] to flag mild and extreme outliers.

Interquartile Range Accumulator

Evaluates IQR = Q3 - Q1 as a robust scale estimator with a 25% breakdown point.

Gaussian Quantile Inversion Unit

Compares empirical quartiles with theoretical normal quantiles z_{0.75} = -z_{0.25} ≈ 0.67449.

Linear Dispersion Regression Unit

Performs linear regression of IQR versus σ to confirm the theoretical 2 · Φ^(-1)(0.75) ≈ 1.349 proportionality factor.

FOLLOW THE METHOD

A reason behind every step.

Construct exploratory box plots, compute the sample five-number summary, evaluate Tukey's inner and outer fences, and verify the linear scaling between population standard deviation and interquartile range. Standardized parameter settings: 1.0, 2.0, 3.0, 4.0, 5.0, 6.0 σ.

01

Set Baseline Scale Parameter and Sample Size

Specify sample standard deviation σ = 1.0 for a centered Gaussian distribution and generate an initial random sample of N = 10,000 observations.

02

Calculate the Five-Number Summary

Sort the sample array and determine the sample minimum x_min, first quartile Q1, median Q2 (50th percentile), third quartile Q3, and sample maximum x_max.

03

Establish Tukey's Fences and Outlier Thresholds

Compute the interquartile range IQR = Q3 - Q1. Construct inner fences at Q1 - 1.5·IQR and Q3 + 1.5·IQR, logging any points beyond these boundaries as statistical outliers.

04

Verify Theoretical Normal Interquartile Range

For a standard normal distribution with σ = 1.0, verify that the theoretical IQR equals 2 · 0.67449 · σ = 1.34898, recording the trial in the laboratory notebook.

05

Step Scale Parameter Across σ = 1.0 to 6.0

Increment the scale parameter σ across standardized values σ ∈ {1.0, 2.0, 3.0, 4.0, 5.0, 6.0}, observing proportional expansion of the box span and whisker lengths.

06

Execute Linear Regression Analysis

Fit a linear regression model y = mx + b to the coordinate pairs (x = σ, y = IQR). Confirm that the empirical gradient m = 1.3490 precisely matches theoretical normal quartile spacing.

YOUR NOTEBOOK · 0 OBSERVATIONS

Turn measurements into empirical insight.

See a complete example report ↗

Points are your recorded observations. The solid regression line validates Box Plots & Tukey's Fences mathematical scaling.

LINEAR REGRESSION FIT · y = mx + b
y = 1.3490 · x
#Population Standard Deviation σ (σ)Interquartile Range IQR (IQR)Standard Deviation σInterquartile Range IQRRemove

No readings yet. Execute a statistical trial and record it.

Calculate it yourself.

CHECK YOUR UNDERSTANDING

Explain what the statistical metrics mean.

What is the theoretical ratio IQR / σ for a Gaussian distribution?

Tukey's inner fences for identifying outliers are placed at:

What is the asymptotic breakdown point of the sample median?

In a box plot, if the upper whisker is much longer than the lower whisker and the median is near Q1, the data is: