NZ Scholarship Statistics

What NZ Scholarship Statistics is

Statistics Scholarship is built on real data and software output, so memorised definitions help far less than reading an unfamiliar display correctly. Entry is through your school, and around 3% of Level 3 statistics students are awarded.

Scholarship Statistics is assessed by one three-hour examination, performance standard 93201. NZQA's 2026 specification says the four questions are set in the areas of statistical investigation, statistical literacy and probability, all in real-life contexts, and that individual questions may cover more than one area. There is an emphasis on data analysis and interpretation. Data sets with statistical output are provided where appropriate, and some questions have minimal scaffolding, so you organise your own answers. You are expected to show all relevant working, with accuracy that suits the context.

The NZ Scholarship Statistics exam in 2026 and 2027

NZQA's 2026 timetable puts Scholarship Statistics on Monday 16 November, in the afternoon session. The 2027 timetable is not out yet: NZQA says exams run from 9 November to 3 December 2027, and at the time of writing it has not published a 2027 Scholarship Statistics specification, so the 2026 one is the latest. The 2026 paper is a printed exam with four questions. You need an approved calculator, and NZQA says a Statistics Formulae and Tables booklet and separate question and answer booklets will be provided.

• Total score 32. The 2025 booklet had four questions and a total score of 32, so each question is worth 8.
• Integrate the areas. NZQA's 2025 report says questions required you to combine skills and knowledge from several areas of the statistics curriculum.
• Level 8 curriculum. The report says you are expected to understand the achievement objectives of the statistics strand up to Level 8, including the concepts in the Level 3 statistics standards.

How NZ Scholarship Statistics is marked

Four questions, each marked 0 to 8, add to 32. Parts have little scaffolding, so you decide what to calculate, and a correct number with no interpretation earns only part of the marks.

NZ Scholarship Statistics cut scores

In 2025 the cohort was 11,649 and 2.96% were awarded. The Scholarship score ranged from 17 to 20 over the three years, the widest swing of the four subjects.

A worked example at Scholarship level

This invented question shows the thinking, not a real exam question. Students chose whether to use a revision app. Of 120 who used it, 36 scored above 80%, and of 110 who did not, 24 did. Is there evidence that the app helps? The sample proportions are 36 ÷ 120 = 0.300 and 24 ÷ 110 = 0.218, a difference of 0.082. The standard error of the difference and a 95% confidence interval are:

Interpret it in context: we are 95% confident that, in the population these students represent, the proportion scoring above 80% is between 3.1 percentage points lower and 19.4 percentage points higher for app users. The interval includes 0, so there is not enough evidence of a difference in the population. A Scholarship answer goes further. Students chose whether to use the app, so this is an observational study, and keener students may be more likely to use it and to score well, so even a clear difference would show association, not cause. It also says which population the result applies to, which depends on how the students were selected. Linking the calculation, the interpretation and the study design is what scores 7 or 8. The same data could be analysed with a bootstrap or re-randomisation distribution, which should give a similar conclusion.

Exam answers

The answers and a worked mark scheme come with today's paper once it is marked. We do not publish official or past paper answers. Every question on the daily paper is our own.

Use the daily paper as a practice exam

Uni-Sine publishes a free daily paper on the NCEA Level 3 Statistics track. It is a short timed paper of 8 questions worth 25 to 35 marks, not a full NCEA exam and not a Scholarship paper, and it is not written by NZQA. It includes hypothesis testing, normal and binomial distributions, sampling, correlation and regression, probability and conditional probability, so it helps with the breadth Scholarship expects. The real exam is three hours of unscaffolded questions, so also practise interpreting software output and writing your own conclusions. See the NCEA Level 3 Statistics guide for the Level 3 standards, including 91584, 91585 and 91586.

What examiners said in 2025

From NZQA's 2025 Scholarship Statistics assessment report:

• Rote answers. Successful candidates showed broad statistical ideas, not rehearsed answers from previous papers.
• Connecting areas. Candidates readily identified the purpose of an experimental study design, but struggled to identify the purpose of a sample-to-population inference study design.
• Language. Questions revealed weaknesses in the use of appropriate statistical language, and candidates often failed to reference the correct population.
• What Outstanding candidates did. They made insightful connections to context, discussed assumptions, sampling and study design in relation to validity and inference, and interpreted re-randomisation distributions, bootstrap distributions and confidence intervals.

Read next

New Zealand · NCEA Level 3NZ Scholarship Chemistry: exam, cut scores, examplesNZ Scholarship Chemistry explained: the 2026 exam date and format, NZQA cut scores for Scholarship and Outstanding 2023 to 2025, and a worked example.