STATS108: nail every assessment, not just read the notes
Your complete guide to University of Auckland's statistics for commerce course. See where the marks are, work real practice questions, and study with an AI tutor that knows STATS108.
Sia generates STATS108 practice questions, walks through datafication and classification step by step, and quizzes you on the material the heaviest assessments weight most heavily.
Worked example
A retailer surveys a random sample of 400 customers and finds 56% would use a loyalty app. Using the standard error of a proportion, what is the approximate 95% confidence interval for the population proportion?
Compute the standard error: the square root of 0.56 times 0.44 over 400, which is the square root of 0.000616, about 0.0248.
Form the interval: 56% plus or minus 5% gives roughly 51% to 61%.
Check the traps: 55% to 57% treats the sample as if it were far larger; 46% to 66% doubles the margin; 'exactly 56%' reports the sample value as if it were the population value.
The trap: Reporting the sample proportion as the answer. The whole point of the interval is that 56% is an estimate; the population value is somewhere in a range whose width depends on the sample size. classic slip!
One exam decides 45% of your grade. At least 45% required in this component. This whole page is built around that.
Overview
What STATS108 is, and where it sits
STATS 108 is the University of Auckland's standard Stage 1 statistics course for Commerce students and for Arts students taking Economics. The catalogue is explicit that its syllabus is the same as STATS 101 with more emphasis on examples from commerce, and that BCom, BProp, BPlan and BArch students should take 108 while BSc and BA students take 101.
The published structure is three modules of four concepts each: modern data technologies and responsibilities (datafication, classification, prediction, randomisation); making and evaluating claims or decisions based on data (estimation, quantification, confirmation, explanation); and designing and communicating about data (variation, distribution, regression, generalisation). The six learning outcomes add data ethics including Māori Data Sovereignty, reproducible technology use, and written summaries of uncertainty.
Assessment is engagement 5%, online tasks and quizzes 30%, an evening online test 20% and a final exam 45% with a 45% minimum. The published workload is 12.5 hours a week with three hours of lectures and regular drop-in sessions. The course runs in Summer Semester, Semester One and Semester Two, and is required to advance in Business Analytics, Finance, and Operations and Supply Chain Management.
Always treat your own course outline and the exam timetable as authoritative.
Difficulty & time commitment
Is STATS108 hard, and how much time does it take?
STATS108 is manageable if you keep a weekly rhythm and treat the back half as the main event. The pattern is consistent: it starts gently and steepens, and the heaviest assessment is the part that separates grades.
The difficulty curve and the assessment weighting point the same way: the back half is harder and worth more. Front-loading effort there is the highest-return decision in the course.
Is this course for you
Who tends to do well, and who tends to struggle
You will likely do well if
- You submit every task on time — the marking scheme gives full marks for full, punctual engagement.
- You want statistics through business examples rather than science ones.
- You can explain a confidence interval and a p-value in a sentence each.
- You use the drop-in sessions when a concept does not land; they are not recorded.
You may struggle if
- You treat the 45% exam floor as a formality; it is independent of your total.
- You skip Module 1's data-responsibility material as soft — it carries two learning outcomes.
- You memorise procedures without the concept behind them; the exam asks for interpretation.
- You leave the tasks until the 10pm deadline and lose the engagement marks.
- For every commerce example, name the population, the sample and the claim before touching any number.
- Practise writing the uncertainty sentence: estimate, interval, and what the interval does and does not say.
- Treat the evening online test as a full rehearsal of the exam's format and timing.
- Keep a list of the twelve module concepts and write a one-line definition and one business example for each.
Syllabus
The 12 topics, concept by concept
The exam-weight marker on each topic shows where the marks concentrate. The amber topics carry the highest exam weight.
T1 · Datafication
Module 1How activity becomes data, and what that means for quality and responsibility.
T2 · Classification
Module 1Sorting units into categories from data, and the errors that follow.
T3 · Prediction
Module 1Using data to predict outcomes and judging predictive performance.
T4 · Randomisation
Module 1Random sampling and random allocation as the basis for valid inference.
T5 · Estimation
Module 2Estimating population quantities from samples, with uncertainty attached.
T6 · Quantification
Module 2Quantifying uncertainty: confidence intervals and their interpretation.
T7 · Confirmation
Module 2Testing claims against data: hypothesis tests and p-values.
T8 · Explanation
Module 2Distinguishing association from explanation and causal claims.
T9 · Variation
Module 3Describing and reasoning about variability in data.
T10 · Distribution
Module 3Distributions as models for data, including the normal model.
T11 · Regression
Module 3Fitting and interpreting simple linear regression.
T12 · Generalisation
Module 3When and how results generalise beyond the data at hand.
How it's assessed
Assessment structure
| Component | Weight | Format & timing |
|---|---|---|
| Engagement | 5% | Engagement with the course activities. Across the semester. Individual coursework. |
| Online tasks and quizzes | 30% | Online tasks and quizzes; tasks marked as a feedback mark plus a final mark, full marks for engaging with all parts and submitting on time; due 10pm. Across the semester. Continual assessment. |
| Online test | 20% | Online test held in the evening. Mid-semester. Individual coursework. |
| Final Exam | 45% | Final examination covering the whole course. Examination period. At least 45% required in this component. |
- Two conditions: at least 50% overall AND at least 45% in the final examination. Coursework cannot compensate for an exam under the floor.
- The final exam is 45% with a 45% minimum, and the 20% online test rehearses it mid-semester. Tasks and quizzes (30%) are marked on engagement and timely submission, so they are the reliable part of the grade if you simply do them.
This is a coursework course. Coursework carries 55% of the grade and the final exam is the single heaviest piece at 45%, so steady work across the semester decides your result more than any one sitting. At least 45% required in this component.
Final exam timing: During the examination period. Confirm the exact date and venue on your exam timetable.
How to actually pass it
A weekly rhythm, two checklists, and the traps to avoid
The course rewards consistency over cramming, and practice over re-reading. Here is the loop that works, then what to have nailed before each exam.
The weekly loop
Before the mid-semester checklist
- Explain datafication, classification, prediction and randomisation with an example each.
- Estimate a population quantity and attach a confidence interval.
- Set up a hypothesis test and interpret a p-value correctly.
- Distinguish association from explanation.
Before the final heaviest topics
- Describe variation and use a distribution as a model.
- Fit and interpret a simple linear regression.
- Judge when a result generalises beyond the sample.
- Write a summary that communicates uncertainty and critique someone else's.
The mistakes that cost marks
Reading the p-value backwards. It measures the data against the null model, not the probability the claim is true.
Interval without interpretation. Reporting the numbers without saying what population quantity they bracket loses the marks the outcome is for.
Missing the exam floor. A strong coursework total still fails if the exam is under 45%.
Formula & concept sheet
The vocabulary and formulas you must own
- Datafication
- Turning activity into recorded data, with implications for quality and responsibility.
- Randomisation
- Random sampling or allocation, which makes inference valid.
- Estimate
- A sample-based value for a population quantity.
- Confidence interval
- A range of plausible values for a population quantity at a stated confidence level.
- Hypothesis test
- A comparison of data with a null model to judge a claim.
- p-value
- How extreme the observed data are under the null model.
- Association
- A relationship in data that need not be causal.
- Distribution
- The pattern of values a variable takes; the normal model is the standard case.
- Regression
- A fitted line describing how one variable changes with another.
- Generalisation
- Extending a result from the sample to a wider population, justified by how the data were collected.
- Māori Data Sovereignty
- The principle that data about Māori is subject to Māori governance, named in the course outcomes.
Set texts
The prescribed reading
The syllabus references map straight onto these.
STATS 108 online coursebook
.
Where it fits
Prerequisites, related courses & why it matters
No prerequisite. Restriction: STATS 101, STATS 102, STATS 107, STATS 191. STATS 108 is 15 points at Stage 1, offered in Summer Semester, Semester One and Semester Two at the City campus, and is the Commerce counterpart of STATS 101.
Your STATS108 study toolkit
Study the course with Sia, not just read about it
Each tool already knows STATS108: your syllabus, your texts, and where the marks are. Grouped by how you study, from first contact to exam week.
FAQ
Frequently asked questions
Is STATS 108 hard?
It rates moderate. The content is applied and conceptual, and 35% of the grade rewards engagement and timely tasks, but the 45% exam has its own 45% floor and the published workload is 12.5 hours a week.
What is the assessment breakdown?
Engagement 5%, online tasks and quizzes 30%, online test 20% and final exam 45%, per the catalogue page. At least 45% in the exam and 50% overall are required.
STATS 108 or STATS 101?
The catalogue says BCom, BProp, BPlan and BArch students enrol in 108; BSc, BA and other degrees enrol in 101. The syllabus is the same; 108 uses commerce examples. You cannot take both.
Do I need prior statistics?
No formal background is required. If your mathematics background is limited the catalogue suggests STATS 100 first.
What changed after student feedback?
The catalogue lists: tasks now get a feedback mark and a final mark with full marks for engaging fully and submitting on time; quiz and task deadlines moved to 10pm; notes and exercises released well ahead; lecture notes reworked to link outcomes, lectures and assessments.
Which majors need it?
The Business School's first-year planning guidance names Business Analytics, Finance, and Operations and Supply Chain Management as majors that require STATS 108 to advance.
Study STATS108 with Sia
Work through datafication, classification, prediction and the rest of the course with a tutor that knows it and quizzes you on the topics the assessments weight most heavily.
Start studying with Sia
