Statistics Quest

Visualising and Exploring Data

Choose, build and read charts that tell the truth about data.

Bar charts, histograms, box and dot plots, density and violin plots, scatter plots, line charts, ECDFs, Q-Q plots and heatmaps — plus misleading charts, accessibility and data storytelling.

Lessons

  1. 1Choosing the right chartChoose a chart from the question you are asking and the types of the variables involved, and explain why other charts would mislead or hide the answer.25 minFree
  2. 2Bar charts for categoriesDraw and read bar charts of categorical data — sorted, grouped or stacked — and report proportions with the right denominator.30 minMembers
  3. 3HistogramsBuild and read a histogram, describe the shape of a distribution, and judge how the choice of bins changes what the chart shows.30 minMembers
  4. 4Box plots and dot plotsBuild a box plot from the five-number summary and the 1.5 × IQR rule, compare groups with side-by-side box plots, and recognise what a box plot hides.30 minMembers
  5. 5Density curves and violin plotsExplain how a kernel density estimate is built, read heights and areas from a density curve, judge the effect of the bandwidth, and choose between violin and box plots.30 minMembers
  6. 6Scatter plotsRead a scatter plot for direction, form, strength and unusual points, use a fitted line to make a prediction, and fix overplotting.30 minMembers
  7. 7Line charts and timeRead trend, seasonality, one-off spikes and structural breaks from line charts, compare like with like over time, and display several series honestly.30 minMembers
  8. 8ECDFs and Q-Q plotsRead proportions, medians and percentiles from an empirical cumulative distribution function, compare groups with ECDFs, and judge departures from normality with a normal Q-Q plot.35 minMembers
  9. 9Correlation heatmapsRead a correlation matrix and its heatmap — sign, strength, redundancy — choose an honest colour scale, and recognise what a single correlation per pair cannot show.30 minMembers
  10. 10Misleading chartsRecognise and quantify the common ways charts mislead — truncated axes, area distortion, cherry-picked windows, dual axes and cumulative totals — and redraw them honestly.30 minMembers
  11. 11Accessible charts and data storiesWrite chart titles that state the finding, label charts so they can be read without a legend hunt, choose colours that work for colour-blind readers, and provide text alternatives and data tables.25 minMembers