All Practice Exams

100+ Free Advanced Higher Statistics Practice Questions

Prepare for the Advanced Higher Statistics (Qualifications Scotland SCQF Level 7) exam with instant access — no signup required.

✓ No registration✓ No credit card✓ No hidden fees✓ Start practicing immediately
100+ Questions
100% Free

Loading practice questions...

2026 Statistics

Key Facts: Advanced Higher Statistics Exam

SCQF Level 7

Scottish Credit and Qualifications Framework undergraduate level 1 equivalent

Qualifications Scotland / SCQF

120 Marks

Total course assessment mark allocation (question paper 1: 30 marks; question paper 2: 90 marks)

Advanced Higher Statistics course specification (version 5.0)

160 Hours

Notional learning time requirement for SCQF Level 7 course completion

Qualifications Scotland Guidelines

3 Hours 45 Minutes

Total written examination time across question paper 1 (1 hour) and question paper 2 (2 hours 45 minutes)

National Qualifications Examination Timetable 2026

Scottish Advanced Higher Statistics (SCQF Level 7) is assessed by two externally marked question papers worth 120 marks in total: paper 1 (30 marks, 1 hour) on interpreting a statistical report, and paper 2 (90 marks, 2 hours 45 minutes) on applying statistical techniques. This 100-question multiple-choice bank is a free study aid for the underlying concepts and calculations; it is not a simulation of the written papers.

Sample Advanced Higher Statistics Practice Questions

Try these sample questions to test your Advanced Higher Statistics exam readiness. Each question includes a detailed explanation. Start the interactive quiz above for the full 100+ question experience with AI tutoring.

1A statistician divides a population of Scottish high school students into subgroups based on local authority area and then takes a simple random sample from within each subgroup proportional to its size. Which sampling method is being used?
A.Stratified random sampling
B.Cluster sampling
C.Systematic sampling
D.Quota sampling
Explanation: Stratified random sampling involves dividing the population into mutually exclusive non-overlapping strata (subgroups) and selecting a simple random sample from each stratum. Proportional allocation ensures each stratum is represented according to its proportion in the total population.
2A researcher selects every 25th household from an alphabetical register of address postcodes in Edinburgh. What type of sampling strategy is being applied?
A.Simple random sampling
B.Systematic sampling
C.Stratified sampling
D.Convenience sampling
Explanation: Systematic sampling selects elements at a constant periodic interval k = N/n from a list after a random starting point. Here, selecting every 25th household directly fits the definition of systematic sampling.
3Which of the following scenarios best illustrates non-response bias in a statistical survey?
A.An interviewer subtly prompts respondents toward a specific answer
B.A telephone poll excludes individuals who do not own a landline telephone
C.A survey sent by email receives responses primarily from individuals with strong positive or negative opinions while others ignore it
D.A measurement device consistently overstates the weight of agricultural yields by 5 grams
Explanation: Non-response bias occurs when individuals selected for a sample fail to respond, and those who choose not to respond differ systematically in their opinions or characteristics from those who do respond. High non-response rates undermine sample representativeness.
4In an experimental trial comparing two crop fertilizers, fields are grouped into blocks based on soil moisture levels before randomly assigning fertilizer types within each block. What is the primary purpose of blocking in experimental design?
A.To prevent Type I errors from occurring during hypothesis testing
B.To eliminate the need for a control group in the experiment
C.To guarantee that the sample size in each treatment group is doubled
D.To reduce nuisance variation attributable to known extraneous factors like soil moisture
Explanation: Blocking is an experimental design technique used to group experimental units with similar nuisance characteristics (such as soil moisture). By accounting for variation between blocks, experimental error is reduced, allowing clearer detection of treatment effects.
5A study compares exam results of students who voluntarily attended extra evening tutoring sessions against those who did not attend. Why cannot causal inferences be drawn directly from this study?
A.It is an observational study subject to confounding variables such as student motivation
B.The sample size is inherently too small to permit statistical inference
C.Observational studies can never yield statistically significant p-values
D.Tutoring sessions are ethically prohibited from being evaluated statistically
Explanation: Because participants self-selected into the tutoring group, confounding variables (such as prior attainment, self-motivation, or socioeconomic background) differ between groups. Observational studies show association, not causation, due to lack of random assignment.
6A list of all registered patients in a health center from which a sample is drawn is technically referred to as what?
A.Target population
B.Sampling frame
C.Sample statistic
D.Census parameter
Explanation: A sampling frame is the actual list or database of elements from which a sample is selected. An inaccurate or incomplete sampling frame leads to coverage bias.
7Which sampling method divides a city into geographic zones, randomly selects 5 zones, and includes every resident within those selected zones in the sample?
A.Simple random sampling
B.Stratified random sampling
C.Single-stage cluster sampling
D.Quota sampling
Explanation: Single-stage cluster sampling divides the population into naturally occurring groups (clusters), randomly selects a subset of clusters, and collects data from all individuals within those selected clusters.
8What key feature distinguishes a double-blind clinical trial from a single-blind trial?
A.The study uses both quantitative and qualitative data collection methods
B.Subjects are randomly assigned to treatments but investigators know the assignments
C.Two separate control groups are utilized instead of one
D.Neither the subjects nor the investigators evaluating outcomes know which treatment subjects receive
Explanation: In a double-blind experiment, neither the participants nor the clinical evaluators know who receives the active treatment versus the placebo. This prevents placebo effects in participants and observer bias in outcome assessment.
9A market research firm stands outside a shopping center on a Tuesday morning to survey passersby about renewable energy policy. What is the main methodological limitation of this approach?
A.It relies on convenience sampling, leading to selection bias as working individuals are underrepresented
B.It requires complex probability weightings that increase variance
C.It produces quantitative data that cannot be analyzed using hypothesis tests
D.It violates the Central Limit Theorem regardless of sample size
Explanation: Sampling individuals available at a single time and location is convenience sampling. Tuesday morning shoppers are unlikely to be representative of the broader population, introducing selection bias.
10In a completely randomized experimental design with 60 participants assigned equally to 3 treatment groups, how are subjects allocated to treatments?
A.Participants are categorized by age before allocating 20 to each group
B.Each participant is assigned to one of the 3 groups with equal probability purely by random allocation
C.The first 20 arriving participants receive treatment 1, the next 20 receive treatment 2, and the rest treatment 3
D.Participants choose their preferred treatment until each group reaches 20
Explanation: A completely randomized design allocates all experimental units to treatment groups entirely at random, ensuring each participant has an equal chance of receiving any of the experimental treatments.

About the Advanced Higher Statistics Exam

Free practice question bank and study resource for Scottish Advanced Higher Statistics (SCQF Level 7), awarded by Qualifications Scotland (formerly the Scottish Qualifications Authority). The course covers data analysis and modelling, statistical inference, and hypothesis testing, and is assessed by two written question papers worth 120 marks in total. Note: the real papers are mark-based short-answer, extended-response and case-study questions; this bank adapts that content into 100 multiple-choice items for revision and cannot reproduce the marks awarded for method, working and contextual interpretation.

Assessment

Two externally assessed question papers: paper 1 (30 marks, 1 hour) analysing a statistical report and interpreting summary statistics, and paper 2 (90 marks, 2 hours 45 minutes) applying statistical techniques from across the course. There is no coursework component.

Time Limit

Question paper 1: 1 hour; question paper 2: 2 hours 45 minutes

Passing Score

Graded A-D, with No Award below D. Notional grade boundaries are 50% of the total course assessment marks for a C, 70% for an A and 85% for an upper A, with grade D from a notional 40%; final boundaries are set each year at awarding meetings after marking.

Exam Fee

No candidate fee is published by Qualifications Scotland: entry fees are invoiced to the presenting centre, so school and college candidates in Scotland are not charged. Private candidates must arrange an approved presenting centre, which sets its own charge. (Qualifications Scotland (formerly SQA))

Advanced Higher Statistics Exam Content Outline

25-45%

Data analysis and modelling

Data handling and interpretation, probability theory, discrete random variables, and the particular probability distributions named in the course - binomial, Poisson, uniform and normal - with expectation, variance and linear combinations of random variables.

25-45%

Statistical inference

Random sampling methods, the central limit theorem, point estimators and standard errors, confidence intervals for means, differences, proportions, paired data and variances, sample-size calculation, and bivariate analysis.

25-45%

Hypothesis testing

Parametric tests (z, one-sample, two-sample and paired t, and the variance-ratio F-test), non-parametric tests including chi-square goodness-of-fit and association, and bivariate tests on correlation and the regression slope.

How to Pass the Advanced Higher Statistics Exam

What You Need to Know

  • Passing score: Graded A-D, with No Award below D. Notional grade boundaries are 50% of the total course assessment marks for a C, 70% for an A and 85% for an upper A, with grade D from a notional 40%; final boundaries are set each year at awarding meetings after marking.
  • Assessment: Two externally assessed question papers: paper 1 (30 marks, 1 hour) analysing a statistical report and interpreting summary statistics, and paper 2 (90 marks, 2 hours 45 minutes) applying statistical techniques from across the course. There is no coursework component.
  • Time limit: Question paper 1: 1 hour; question paper 2: 2 hours 45 minutes
  • Exam fee: No candidate fee is published by Qualifications Scotland: entry fees are invoiced to the presenting centre, so school and college candidates in Scotland are not charged. Private candidates must arrange an approved presenting centre, which sets its own charge.

Keys to Passing

  • Complete 500+ practice questions
  • Score 80%+ consistently before scheduling
  • Focus on highest-weighted sections
  • Use our AI tutor for tough concepts

Advanced Higher Statistics Study Tips from Top Performers

1Master Linear Combinations of Random Variables: Ensure fluency with expectation E(aX + bY) = aE(X) + bE(Y) and variance Var(aX + bY) = a^2 Var(X) + b^2 Var(Y) for independent variables.
2Identify the Correct Statistical Test: Practice distinguishing when to apply a z-test, one-sample t-test, two-sample t-test (pooled vs unpooled variance), paired t-test, chi-square test or the variance-ratio F-test based on the data structure and the assumptions you can justify.
3Understand Type I and Type II Errors: Be clear that Type I error rate is alpha (rejecting a true H0), while Type II error rate is beta (failing to reject a false H0), and power is 1 - beta.
4Check Model Diagnostics in Regression: Always inspect residual plots for linearity, constant variance (homoscedasticity), and independence before trusting linear regression results.

Frequently Asked Questions

What is the assessment structure for Advanced Higher Statistics?

Two externally assessed question papers, 120 marks in total. Question paper 1 is worth 30 marks in 1 hour and asks candidates to analyse a statistical report and interpret summary statistics. Question paper 2 is worth 90 marks in 2 hours 45 minutes and applies statistical techniques from across the course. Unusually for an Advanced Higher, there is no coursework or project component.

How does Advanced Higher Statistics differ from Higher Mathematics or Higher Applications of Mathematics?

Advanced Higher Statistics is set at SCQF Level 7 and is built from three mandatory areas - data analysis and modelling, statistical inference, and hypothesis testing. It goes well beyond the statistics strand of Higher Mathematics into probability models, confidence intervals, parametric and non-parametric tests, and bivariate analysis.

Which probability distributions are examined in Advanced Higher Statistics?

The syllabus includes discrete distributions (Binomial, Poisson) and continuous distributions (Uniform, Normal, Student's t, Chi-square, and F), as well as normal approximations to discrete distributions.

Are statistical tables provided in the SQA examination?

Yes, candidates are provided with SQA Statistics Formulae and Tables containing cumulative probabilities, critical values for z, t, Chi-square, F, and Spearman's rank correlation, alongside essential formulae.