Exploring data and finding useful patterns.
Profile the evidence, inspect distributions, compare groups and explain useful patterns without mistaking them for causes.
Find a pattern.
Check what it means.
Move from a clear analysis plan to a careful exploration of the evidence. Profile the source, inspect response durations, compare groups and challenge the headline with composition and missingness checks.
Before you start: Applied Data Analysis Module 1 or equivalent understanding of grain, cohorts, denominators and descriptive versus causal questions. A calculator or local spreadsheet is sufficient; Python is optional.
Allow about 5 hours and 10 minutes, including exercises. Work with a calculator, text editor or local spreadsheet. Every lesson includes a detailed explanation, practical task, worked solution and knowledge check.
Reuse Module 1’s source unchanged. Learn with a calculator or spreadsheet; optional read-only Python reproduces the outputs. This is a descriptive investigation, not a causal evaluation. Explore practical lessons, worked examples and projects. Follow a published path, practise the method and build work you can explain.
Six lessons. One evidence-led investigation.
Profile the extract before looking for patterns
Reconcile rows, keys, types and missing fields before interpretation.
Understand distributions instead of relying on one average
Calculate response durations with consistent units.
Choose charts that reveal rather than manufacture patterns
Match a chart to a distribution, comparison or composition question.
Compare groups and separate composition from performance
Calculate group-specific rates and reconcile their denominators.
Investigate missingness and alternative explanations
Profile missing ratings by group rather than only overall.
Turn explored patterns into an evidence note
Write a concise finding with source fractions and limitations.
A real practice task.
A manageable dataset.
Start with the profile and worksheet, then build your own summaries and chart plans. The complete pack has thirteen offline files, including a styled worked exploration and optional read-only Python source.
Snapshot: 22 June 2026 00:00 UTC. The cohorts are 1–7 and 8–14 June. Missing ratings remain missing. The same fictional case connects the Applied modules and is separate from Northstar Shop. No real company outcome or customer data is represented.
Can you explain the pattern and its limits?
Review source checks, summaries, visual boundaries, weighted groups and interpretation. Aim for eight points with no zero in summaries or interpretation. This self-review is not an accredited assessment or operational approval.
Begin Module 02 →Return to Applied Data Analysis ↗
Explore practical lessons, worked examples and projects. Follow a published path, practise the method and build work you can explain. Keep your work locally; no upload is required.