Statistics Quest · part of Formula Quest
Learn statistics by analysing realistic data.
Not formula memorisation: you explore data, choose a method, run the calculation, check its assumptions and explain what the result means — with specific feedback on every step.
Not sure where to start? Take the free placement check — it recommends a starting track.
Free lessons, the lab and the dataset library need no membership. Sign in with your Formula Quest account to save progress.
A live example from Track 2
Is the “average commute” typical?
Show the data as a table
| From | To | Count |
|---|---|---|
| 4 | 11.2 | 16 |
| 11.2 | 18.4 | 25 |
| 18.4 | 25.6 | 43 |
| 25.6 | 32.8 | 40 |
| 32.8 | 40 | 29 |
| 40 | 47.2 | 36 |
| 47.2 | 54.4 | 12 |
| 54.4 | 61.6 | 13 |
| 61.6 | 68.8 | 3 |
| 68.8 | 76 | 6 |
| 76 | 83.2 | 4 |
| 83.2 | 90.4 | 5 |
| 90.4 | 97.6 | 1 |
| 97.6 | 104.8 | 0 |
| 104.8 | 112 | 2 |
| 112 | 119.2 | 0 |
| 119.2 | 126.4 | 2 |
| 126.4 | 133.6 | 2 |
| 133.6 | 140.8 | 0 |
| 140.8 | 148 | 1 |
01
Learn the idea
Short explanations, formulas with every symbol defined, worked examples with real numbers, and interactive demonstrations you can change.
02
Do the analysis
Calculate on realistic datasets, choose methods, set parameters, run tests and fit models — in the lesson or in the lab.
03
Get feedback that teaches
Answers are graded on our server. Wrong answers get specific feedback: “you used the population SD, the question asks for the sample SD”, not just “incorrect”.
The curriculum
16 tracks · 175 lessons · 1,324 graded exercises · 23 applied cases and capstones · 32 datasets
- 01Statistical ThinkingWhat statistics is for, and how data are produced, before any formula.
- 02Describing DataSummarise a dataset with the right measures of centre, spread and shape.
- 03Visualising and Exploring DataChoose, build and read charts that tell the truth about data.
- 04ProbabilityThe rules of chance, conditional probability and Bayes' theorem.
- 05Probability DistributionsThe models behind data and inference, from the binomial to the F distribution.
- 06Sampling and the Central Limit TheoremHow samples behave, and why averages become predictable.
- 07Estimation and Confidence IntervalsEstimate unknown quantities and state the uncertainty honestly.
- 08Hypothesis TestingTest claims with data and draw defensible conclusions.
- 09Correlation and RegressionModel relationships between variables, and know the limits.
- 10Comparing Groups and Categorical DataCompare several groups and analyse counts and tables.
- 11Experiments and A/B TestingDesign, analyse and decide from controlled experiments.
- 12Time Series and ForecastingDescribe, model and forecast data that change over time.
- 13Resampling and Statistical ReasoningSimulation-based inference and healthy scepticism.
- 14Practical Data AnalysisFrom a raw file to a defensible, reproducible analysis.
- 15Applied Statistics for ProfessionalsStatistics as used in business, finance, HR, operations, marketing and research.
- 16Advanced FoundationsBayesian inference, multivariate methods and causal thinking.
A statistics lab in your browser
Pick a dataset — or import your own CSV, which never leaves your browser — and work the way analysts do.
- Explore and filter data, profile every column, and add derived columns from safe expressions
- Group summaries with intervals, percentiles under any of nine conventions, frequency and two-way tables
- Histograms, box plots, scatter plots, Q-Q plots, ECDFs and correlation heatmaps
- A hypothesis-test workbench that shows hypotheses, assumption checks, results and a correctly worded interpretation
- Linear and logistic regression with diagnostics and prediction intervals
- A/B test analysis and experiment sample-size planning
- Forecasting with holdout evaluation, and control charts with capability analysis
- A report builder with Markdown and printable HTML export
Calculations you can trust
The statistical engine is tested against independent references — mpmath at 40 digits, SciPy, statsmodels and the NIST certified regression datasets — with documented tolerances.
Honest data
Every built-in dataset is synthetic and documented: realistic skew, outliers, missing values and confounding, without describing any real person or organisation.
Progress that means something
A lesson is complete only when every exercise is answered correctly. Certificates require a passed, timed skill check; they record completed coursework and are not an academic accreditation.
Applied cases and capstones
- Case · RetailDid the promotion work?Estimate the sales lift of a chain-wide discount promotion fairly — separating it from holidays and store mix — put an honest interval on it, and decide whether it pays for itself.
- Case · OperationsStaffing the contact centreUse hourly call data to model arrivals as Poisson, plan staffing to a demand quantile rather than the average, and connect waiting times to abandoned calls.
- Case · BankingDefault rates in a loan bookEstimate default rates with honest intervals, compare segments, fit a logistic regression and interpret odds ratios — and keep risk prediction separate from causal claims.
- Case · HRCan we trust the engagement survey?Check response rates and response quality, summarise Likert items properly, and correct an engagement headline for nonresponse bias with post-stratification weights.
- Case · LogisticsDid the new routing cut delivery times?Choose between paired and independent analyses, estimate the saving with an interval and an effect size, check assumptions, and judge what a before–after study can and cannot show.
- Case · Public healthEvaluating a screening programmeBuild the 2×2 table, estimate sensitivity and specificity with intervals, and show why predictive values depend on base rates — then decide who the programme should target.
Free to start, included with Formula Quest memberships
Tracks 1 and 2, the first lesson of every other track, the lab, the dataset library and the methods reference are free. The full curriculum, cases, capstones, assessments and certificates are included with Formula Quest memberships, managed on Formula Quest together with your account and billing.