Drawing a whisker out to an outlier
When a value is a possible outlier, the whisker stops at the most extreme value that is not an outlier, and the outlier is marked with its own dot.
General Mathematics · Unit 2 · Topic 5
Summarise data with five-number summaries and box plots, identify possible outliers with the rule, and compare groups with parallel box plots and summary statistics, reporting the differences in context.
Summarise a data set with its minimum, quartiles, median and maximum, and draw those five numbers as a box plot on a labelled scale.
Read a five-number summary, range and IQR off a box plot, use its four quarters to estimate percentages and counts, describe its shape, and know what a box plot cannot show.
Decide which values are possible outliers using the fences and , show them on a box plot, and decide what to do about them.
Draw box plots for two or more groups on one scale, then compare their medians, IQRs, ranges, shapes and outliers and say what the differences mean in context.
Calculate the mean, median, range, IQR and standard deviation of each group with technology, choose the statistics that suit the data, and interpret the differences in context.
Answer a statistical question about groups with a systematic, concise report that compares centre, spread, shape and outliers in context and ends with a justified conclusion.
Ten questions across the topic, from foundation to complex unfamiliar. Your results feed your mastery.
Is Longreach really hotter than Brisbane in January? Do students who catch the bus take longer to get to school? Does one machine fill packets more consistently than another? Each of these questions compares one numerical variable across two or more groups, and that is what this topic is about.
You will build a five-number summary and draw it as a box plot, use the rule to decide which values are possible outliers, and line up box plots on a common scale to compare groups. Then you will compare groups with the mean, median, range, IQR and standard deviation, choose the statistics that suit the data, and write up what you found the way QCAA markers want it: systematic, concise and in the context of the data.
It builds directly on Univariate data analysis 1, so have its quartile method (the medians of the lower and upper halves) and the sample standard deviation ready.
Builds on Univariate data analysis 1.
Subject matter from the General Mathematics General senior syllabus 2025 v1.3 (opens in a new tab), CC BY 4.0 © State of Queensland (QCAA).
The focus areas you can practise on their own. Each one maps to dot points above.
Five-number summaries
Find the minimum, lower quartile, median, upper quartile and maximum from a list, a stem-and-leaf plot or a frequency table.
Drawing box plots
Draw a box plot on a labelled scale, with whiskers to the most extreme values that are not outliers and outliers marked separately.
Reading box plots
Read the five-number summary, range and IQR from a box plot, use the four quarters to estimate percentages and counts, and describe the shape.
Identifying outliers
Calculate the fences $Q_1 - 1.5 \times \text{IQR}$ and $Q_3 + 1.5 \times \text{IQR}$ and decide which values are possible outliers.
Comparing with parallel box plots
Compare groups on a common scale by median, IQR, range, shape and outliers, and interpret the differences in context.
Comparing with summary statistics
Calculate and compare the mean, median, range, IQR and standard deviation of groups, choosing the statistics that suit the shape of the data.
Reporting a comparison
Write a systematic, concise comparison of groups (centre, spread, shape, outliers and a conclusion) in the context of a statistical question.
When a value is a possible outlier, the whisker stops at the most extreme value that is not an outlier, and the outlier is marked with its own dot.
Each whisker and each half of the box holds about 25% of the data, whatever its length. A long section means those values are more spread out, not that there are more of them.
The rule is , with "less than or equal to". A value exactly equal to a fence is not an outlier.
The fences use the IQR, and they are measured from the quartiles: and , not from the median or the mean.
"Group A has a median of 12 and Group B has a median of 15" only states values. A comparison says which is larger and what that means: "the median for Group B is 3 minutes higher, so Group B students typically took longer".
Compare medians with IQRs (both resistant) or means with standard deviations (both use every value). If either group is skewed or has outliers, use the median and IQR.
Parallel box plots must share one scale. Box plots drawn on separate axes can look alike even when the data are very different.
Every comparison names the variable, the groups and the units: "Longreach's median maximum temperature was about 7 °C higher than Brisbane's", not "B is higher".
For a five-number summary, show the ordered data, the median position and the halves you used for and .
For outliers, show the working: , , both fences, then state which values (if any) lie outside them.
When you construct a box plot, use a labelled, evenly spaced scale with units, end the whiskers at the most extreme non-outliers, and mark each outlier with a dot.
Compare means: say which group is larger and by how much for both centre and spread, then interpret. Quote the statistics with units.
A systematic comparison covers centre, spread, shape and outliers, in that order, and ends with a conclusion that answers the question asked.
Use comparative words: higher, lower, more variable, more consistent, typically. "Typically" signals that you are talking about the median or the mean, not every individual.
Choose the median and IQR when either group is skewed or has outliers, and say why. Use the mean and standard deviation for symmetric data without outliers.
Standard deviations come from your calculator: give and round as the question asks.
Check reasonableness: a quartile lies between the minimum and maximum, a fence can be outside the data, and an IQR or standard deviation is never negative.
The Bureau of Meteorology compares climate statistics for Australian towns, such as the median and spread of January maximum temperatures.
NAPLAN and school reports compare the spread of results across schools and year levels.
Hospitals compare emergency department waiting times across days and sites, where a few very long waits make the median the fair summary.
Manufacturers compare machines by the mean and standard deviation of fill volumes, to keep packets close to the label.
Sports scientists compare athletes' times across training programs, using box plots to spot unusually fast or slow performances.
Real estate reports compare median rents across suburbs and cities.