Skip to main content
ScotlandStatisticsSyllabus dot point

How do you plan, carry out and communicate a complete statistical investigation?

Conduct a statistical investigation that draws together the skills of the course: pose a question, plan and collect data, select and apply appropriate analysis, and communicate justified conclusions with their limitations.

An overview of the statistical investigation in SQA Advanced Higher Statistics: how the skills of design, analysis and inference are combined to pose a question, collect and analyse data, and communicate justified conclusions with their limitations, as examined in the question papers.

Generated by Claude Opus 4.810 min answer

Reviewed by: AI editorial process; not yet individually human-reviewed

Have a quick question? Jump to the Q&A page

Jump to a section
  1. What this dot point is asking
  2. The investigation cycle
  3. Choosing the right analysis
  4. Communicating conclusions
  5. Try this

What this dot point is asking

A statistical investigation is where the whole course comes together. Rather than a single technique, the SQA asks you to run the full cycle: turn a real question into a statistical one, plan and collect suitable data, choose and apply the right analysis, and communicate a justified conclusion with its limitations. The investigation skill is assessed through the question papers, where you must select methods and interpret results in context rather than simply execute a named calculation.

The investigation cycle

Every investigation moves through the same four stages, and a good answer shows each one explicitly.

  • Pose the question. Translate a real-world question into a statistical one with clear hypotheses or a quantity to estimate, identifying the population and the variables involved.
  • Plan and collect. Decide on a sampling method (simple random, systematic or stratified) or an experimental design (with control, randomisation, replication and blocking), so the data can actually answer the question without bias.
  • Analyse. Explore the data first, then select the technique that matches the question and the data type, and check that its assumptions are reasonable before applying it.
  • Communicate. State the conclusion in the context of the original question, in language a non-specialist can follow, and acknowledge the limitations.

Choosing the right analysis

The single most examined skill is matching the analysis to the situation, because the question papers deliberately present unfamiliar contexts.

Communicating conclusions

Communication is explicitly examinable: the spec asks you to communicate conclusions reached on the basis of statistical analysis.

Try this

Q1. An investigator has paired before-and-after measurements on the same individuals. Name the analysis that exploits the pairing. [1 mark]

  • Cue. A paired t-test (or, if normality is doubtful, a Wilcoxon signed-rank test), because the pairing removes between-individual variation.

Q2. State why a conclusion should always include the study's limitations. [1 mark]

  • Cue. Because the validity of any statistical conclusion depends on the sampling and the test's assumptions, and significance does not establish importance or causation, so limitations make the conclusion honest and usable.

Exam-style practice questions

Practice questions written in the style of SQA exam questions on this dot point, with worked answer explainers. The year tag is the paper they imitate, not the source.

AH style: choose analysis3 marksAn investigator wants to know whether a new teaching method changes mean test scores. They have scores for a group taught the new way and a separate group taught the old way. Outline the steps of the investigation and name a suitable analysis.
Show worked answer →

State the question as testable hypotheses: H0H_0 that the two population mean scores are equal against H1H_1 that they differ (1 mark).

Plan and check the data: confirm the two groups are independent and consider whether the scores are approximately normal, which determines whether a parametric test is appropriate (1 mark).

Select and justify the analysis: a two-sample (independent) t-test compares the means; if normality is doubtful, a non-parametric Mann-Whitney test is the alternative. Conclude in context and note limitations such as how the groups were formed (1 mark). Markers reward the hypotheses, the planning and assumption check, and a justified choice of test.

AH style: communicate3 marksAfter a hypothesis test gives a p-value of 0.030.03 at the 5%5\% level, write a conclusion in context for a non-specialist, and state one limitation that should accompany it.
Show worked answer →

Since the p-value 0.030.03 is less than the significance level 0.050.05, reject H0H_0: there is significant evidence at the 5%5\% level of a real effect, stated in the context of the study (for example "the new fertiliser gives a higher mean yield") (1 mark).

Communicate it plainly for a non-specialist: the result is unlikely to be due to chance alone, though it does not prove a large or important effect, only a detectable one (1 mark).

State a limitation: for example the conclusion depends on the sample being representative and the test's assumptions holding, and statistical significance is not the same as practical importance (1 mark). Markers reward a contextual conclusion, clear communication and a sensible limitation.

Related dot points

Sources & how we know this