HumachLearnLearn · explore · apply
Start learning
Exploratory Data Analysis · Lesson 60

EDA Checklist

An EDA checklist is a repeatable sequence of questions that prevents exploratory analysis from becoming a random collection of plots.

ConceptWorked examplePracticeKnowledge check
Textbook walkthrough

EDA Checklist

An EDA checklist is a repeatable sequence of questions that prevents exploratory analysis from becoming a random collection of plots. A useful checklist covers row grain/schema, data quality, univariate distributions, important group comparisons, relationships, anomalies and the assumptions that later modelling or reporting will depend on.

Learning goal: explain why EDA Checklist behaves this way, apply it to a small example, and verify the result independently. Begin by being able to justify this first step: Confirm the observational unit, keys, shape and types.

Deeper walkthrough

Read EDA Checklist as a mechanism, not a recipe

Treat this as a sequence of observable decisions rather than one opaque command. Stage 1: Confirm the observational unit, keys, shape and types. Stage 2: Quantify missingness, duplicates and invalid categories/ranges. Stage 3: Inspect distributions of important variables. Final checkpoint: Write observations as evidence and questions, not unsupported causal conclusions.

Mechanism

Follow the transformation

Confirm the observational unit, keys, shape and types.

Quantify missingness, duplicates and invalid categories/ranges.

Inspect distributions of important variables.

Evidence

Know what would convince you

  • Recompute one result from a handful of source rows or an independent formula.
  • Check row counts, group totals and units before interpreting differences.
Useful distinctionDefinition: The exact metric/selection/comparison being computed.
Click a stage to inspect what happens, what changes, and what should be checked before moving on.
Stage 1

Confirm the observational unit

Confirm the observational unit, keys, shape and types. This is an input-preparation stage for EDA Checklist. Verify the relevant type, shape, units, keys, missingness or assumptions before later steps depend on them.

State focus: identify exactly what changed at this stage and what observable evidence confirms that change.
How it works

Trace the mechanism step by step

  1. Confirm the observational unit, keys, shape and types.
  2. Quantify missingness, duplicates and invalid categories/ranges.
  3. Inspect distributions of important variables.
  4. Compare key measures across relevant groups and time.
  5. Inspect relationships and potential confounding/leakage signals.
  6. Write observations as evidence and questions, not unsupported causal conclusions.
Worked demonstration

Structured exploration

1 Schema/grain
2 Missing/duplicates
3 Distributions
4 Group comparisons
5 Relationships
6 Outliers/anomalies
7 Findings + questions
Expected / illustrative result
The checklist provides coverage while still allowing topic-specific exploration when evidence suggests it.
Interpret the result.

For EDA Checklist, trace representative input values into the result and verify shape, dtype, row grain, axis or key behaviour that the operation can change.

Distinctions & related ideas

Place the concept correctly

DefinitionThe exact metric/selection/comparison being computed.
EvidenceTable, formula or visual that answers the question.
AuditIndependent count/total/rule check that can reveal an error.
Use deliberately

When it is appropriate

Use EDA Checklist when it answers a defined question in Exploratory Data Analysis and its inputs/assumptions match the current data or program state.

Boundary conditions

When to stop or reconsider

Reconsider EDA Checklist when the required information is unavailable, the operation would violate a validation/data boundary, or a simpler operation answers the question more transparently.

Common mistakes

Failure modes to recognise

  • Changing the population/grain without noticing it.
  • Using an undefined denominator, time window, unit or category rule.
  • Presenting a number/plot without reconciling it to source counts or totals.
Verification

How to check the result

  • Recompute one result from a handful of source rows or an independent formula.
  • Check row counts, group totals and units before interpreting differences.
  • Change one source value and predict which reported value/mark should change.
Hands-on practice

Demonstrate understanding

Try this:

Construct a tiny example of EDA Checklist. First confirm the observational unit, keys, shape and types. Then quantify missingness, duplicates and invalid categories/ranges. Predict the result before execution and explain one boundary or failure case.

Use 4–8 rows containing the exact key/category/missing-value pattern. Trace one row or group from input to output.
Knowledge check

Check reasoning, not memorisation

Which approach best demonstrates understanding of EDA Checklist?

Quick reference

Remember the logic

Step 1Confirm the observational unit, keys, shape and types.
Step 2Quantify missingness, duplicates and invalid categories/ranges.
Step 3Inspect distributions of important variables.
Step 4Compare key measures across relevant groups and time.
Lesson summary

What to remember

  • An EDA checklist is a repeatable sequence of questions that prevents exploratory analysis from becoming a random collection of plots. A useful checklist covers row grain/schema, data quality, univariate distributions, important group comparisons, relationships, anomalies and the assumptions that later modelling or reporting will depend on.
  • Confirm the observational unit, keys, shape and types.
  • Changing the population/grain without noticing it.
  • Recompute one result from a handful of source rows or an independent formula.