Module 3 · Lesson 12 of 17

Descriptive statistics and graphical summaries

← Back to moduleBack to academy

Learning objectives

  • Compute and interpret centre, spread and shape statistics.
  • Choose the correct graph before formal tests.
  • Detect outliers and stratification opportunities.

Summarise before you test

  • Count, missingness, mean, median, standard deviation, range, quartiles, IQR.
  • Histogram, box plot, run chart and stratified views.
  • Robust summaries when outliers are present.

Garment-factory example

Wash shrinkage may have a mean within tolerance but a long upper tail concentrated in one fabric lot — visible on a stratified box plot but hidden in a headline average.

Method

  1. Clean the data and record how.
  2. Display raw distribution before any summary.
  3. Report both mean and median; investigate their gap.
  4. Stratify by the most plausible contextual factor.

Common mistakes

  • Deleting outliers automatically.
  • Reporting precision beyond instrument resolution.

Knowledge check

Pick one answer per question. Explanations appear after you submit.

  1. 1. The median is preferred over the mean when:

  2. 2. A stratified box plot helps to:

Author: Sanjeewa Dehiwalage · Last reviewed: 2026-07-21

Stay in touch

New chapters, delivered quietly.

A short note when a new story, reflection or milestone is added. No noise, no spam — unsubscribe with a single click.