Statistics Quest

Practical Data Analysis

From a raw file to a defensible, reproducible analysis.

Importing data, variable types, missing values, duplicates and invalid entries, cleaning decisions, grouping and aggregation, transformations, an exploration workflow, choosing methods, and reporting — without needing to code.

Lessons

  1. 1Importing dataImport a CSV file, read the import check, and verify that what was loaded matches the file before analysing anything.25 minFree
  2. 2Setting variable typesCheck the type the software inferred for every column, recognise the classic inference errors, and set each variable to the type its meaning requires.25 minMembers
  3. 3Finding and handling missing valuesFind every form of missing value in a dataset — blanks, tokens, sentinel codes and placeholder text — count them, and choose and document a defensible way to handle them.30 minMembers
  4. 4Duplicates and invalid valuesFind exact and near duplicates, inconsistent categories, impossible values and unit errors in a raw table, and count how many records each problem affects.30 minMembers
  5. 5Making and documenting cleaning decisionsTurn data-quality findings into explicit cleaning rules, log how many records each rule changes, and measure how cleaning changes the results.35 minMembers
  6. 6Grouping and aggregationSummarise a variable within groups, build pivot-style tables of counts and percentages, and combine group results correctly.30 minMembers
  7. 7Transforming variablesChoose and apply a log transformation, a ratio, binning or standardisation, and interpret results on the transformed scale.35 minMembers
  8. 8An exploration workflowExplore a dataset in a disciplined order — question, data, one-variable summaries, charts, relationships — and turn what you see into tentative hypotheses rather than conclusions.30 minMembers
  9. 9Selecting a methodChoose a statistical method by matching the question, the type of outcome and the structure of the data — and recognise when a tempting method does not fit.30 minMembers
  10. 10Writing an analysis reportWrite an analysis report whose results carry their uncertainty and whose limitations and recommendation follow honestly from the evidence.30 minMembers
  11. 11Reproducible analysisRecord an analysis so that anyone — including you in six months — can re-run it from the raw file and get the same numbers.25 minMembers