The idea, step by step
Classify the meaning, not the code
Nominal categories have no natural order, such as travel method. Ordinal categories are ordered, such as low/medium/high satisfaction, but gaps need not be equal. Discrete numerical variables count values; continuous variables measure quantities.
A number used as a label remains categorical. Averaging bus-route codes 100 and 200 does not create a meaningful typical route.
Build a clean record
Use one case per row and clearly defined variables per column, with units in headings. Apply the same procedure and period to every case. Primary data are collected for this question; secondary data already exist from another purpose.
Check duplicates, implausible values, units and missing responses against original records. A blank is not zero. Correct verified errors, preserve genuine extremes, and document decisions. Collect only personal details needed for the question.
A common trap
Missing answers should be zero so software works.
Instead: Missing is not a measured zero; coding it as zero distorts results.
See the thinking
Classify four variables
Classify favourite sport, number of sessions, race time and low/medium/high satisfaction.
- Sport has unordered categories.
- Sessions count; time measures.
- Satisfaction has ordered categories.
Investigate mixed units
A height column in cm has 168, 172, 1.65, blank and 0.
- Check whether 1.65 was recorded in metres before converting to 165 cm.
- A blank is missing; zero is implausible for a student height.
- Keep a record of confirmed changes.
Check your understanding
Is postcode continuous numerical data?
Show answer
No; it is a categorical code.
Differences in codes do not measure distance.
Your turn
6 questions · 12 marks · Work at your own pace.
Read the questions online
- Classify books borrowed weekly.2 marks
- Classify classroom temperature.2 marks
- Classify poor/satisfactory/good/excellent ratings.2 marks
- A time column mixes hours and minutes. What is required?2 marks
- Two rows have the same student/date. What should be checked?2 marks
- Give an advantage and limitation of government secondary data.2 marks
Read the worked solutions
Equivalent correct methods earn the corresponding marks. Include units where asked.
- Classify books borrowed weekly.2 marks
It counts whole books.
Discrete numerical. - Classify classroom temperature.2 marks
It is a measured quantity.
Continuous numerical. - Classify poor/satisfactory/good/excellent ratings.2 marks
The categories have an order, not necessarily equal gaps.
Ordinal categorical. - A time column mixes hours and minutes. What is required?2 marks
0.5 hour is 30 minutes.
Verify then convert all values to common units. - Two rows have the same student/date. What should be checked?2 marks
Delete only a confirmed duplicate under a documented rule.
Whether there is a duplicate entry or two legitimate observations. - Give an advantage and limitation of government secondary data.2 marks
Check source and coverage before use.
It saves collection effort; definitions/date/population may not match the question.
Curriculum reference & lesson scope
SACE Board of South Australia
Stage 1 General Mathematics: statistical investigation, univariate data, sampling, displays, summaries and interpretation.
Official curriculum source ↗