STATS207: pass the exams, not just read the notes
Your complete guide to University of Auckland's data-centered investigation and analysis course. See where the marks are, work real practice questions, and study with an AI tutor that knows STATS207.
Sia generates STATS207 practice questions, walks through types of investigation and designing your own investigation step by step, and quizzes you on the material the exam weights most heavily.
Sharpen your argument
Your group wants to investigate whether students who commute longer sleep less. What is the strongest project design?
Start from what the department asks for: hands-on experience in research design and execution. The design is the assessed artefact, not just the finding.
Match the sampling to the claim. Both variables must come from the same respondents, otherwise there is no association to measure. A defined population with a systematic sampling method is what makes the result generalisable to anything.
Name the confounders. Employment, age, year of study and living arrangement all plausibly affect both commute and sleep. Stating what you cannot control is not a weakness in the report — it is the part that shows you understand what your design can support.
The weaker choice: Option B mistakes sample size for sample quality: a self-selected social media sample is biased regardless of how large it grows. Option C compares aggregates and then draws a conclusion about individuals, which is the ecological fallacy. Option D collects data with no defined population or measure, which produces an anecdote. All three are common project choices and all three cap the mark, because the design is what is being assessed. watch this!
One exam decides 50% of your grade. Dual pass: at least 45% required in this component alone. This whole page is built around that.
Overview
What STATS207 is, and where it sits
STATS 207 is the University of Auckland's practical data analysis course, and the department describes it as a practical course in the statistical analysis of data with hands-on experience in research design and execution. It sits alongside STATS 201 and 208 — you may take only one of the three — and shares their final examination.
What makes STATS 207 distinct is stated plainly by the department: the primary coursework assessment is a self-selected group project, and the course has no mid-semester test. Where its siblings assess through a test, this one assesses through an investigation you choose and run yourself.
That difference changes how the course should be approached. The project is 30% of the grade and its quality depends on choosing a question you can actually answer with data you can actually get. The remaining coursework is a 20% assignment, and the shared final examination carries 50%.
Always treat your own course outline and the exam timetable as authoritative.
Difficulty & time commitment
Is STATS207 hard, and how much time does it take?
STATS207 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 choose a project question you can actually answer with data you can actually get.
- You define your variables operationally before collecting anything.
- You prepare for the shared examination on the standard syllabus, not on your project topic.
- You state the limits of your design rather than hoping the marker misses them.
You may struggle if
- You assume no mid-semester test means less work; the project simply moves that work across the whole semester.
- You mistake a large self-selected sample for a representative one.
- You draw conclusions about individuals from group averages.
- You let the project crowd out examination preparation, when the examination is 50% with a 45% threshold.
- Write your research question as a single sentence containing both variables and the population. If you cannot, the design is not settled.
- Pilot your data collection on a handful of respondents before running it; ambiguous questions surface immediately.
- Report effect size and uncertainty, not only whether a result was significant.
- Practise the shared examination with past STATS 201 and 208 papers, since it is the same paper.
Syllabus
The 12 topics, topic by topic
The exam-weight marker on each topic shows where the marks concentrate. The amber topics carry the highest exam weight.
T1 · Types of investigation and study design
Course description (research design)Observational and experimental designs, and what each can support.
T2 · Designing your own investigation
Course description (self-selected project)Turning an interest into a question that data can answer.
T3 · Data collection and execution
Course description (hands-on execution)Gathering data in practice, and the compromises that arise.
T4 · Exploring and summarising data
Standard Stage II data analysis canonGraphical and numerical exploration before any modelling.
T5 · Inference for means and proportions
Standard Stage II data analysis canonConfidence intervals and tests for the basic comparisons.
T6 · Comparing groups
Standard Stage II data analysis canonTwo-sample and multi-group comparison, including analysis of variance.
T7 · Simple linear regression
Standard Stage II data analysis canonFitting, interpreting and checking a straight-line relationship.
T8 · Multiple regression
Standard Stage II data analysis canonSeveral predictors at once, and what changes when they are correlated.
T9 · Model checking and diagnostics
Standard Stage II data analysis canonResiduals, assumptions, and knowing when a model should not be trusted.
T10 · Categorical data analysis
Standard Stage II data analysis canonTables of counts and tests of association.
T11 · Reporting an analysis
Course description (project)Communicating what the data support, and what they do not.
T12 · Working as a project group
Course description (group project)Dividing an investigation without losing coherence.
How it's assessed
Assessment structure
| Component | Weight | Format & timing |
|---|---|---|
| Final examination | 50% | Final examination, shared with STATS 201 and STATS 208. Examination period. Dual pass: at least 45% required in this component alone. |
| Group project | 30% | A self-selected group project, published by the department as the primary coursework assessment. Across the semester. Continual assessment. |
| Assignment | 20% | Assignment. Across the semester. Continual assessment. |
- You must obtain at least 50% overall AND at least 45% in the final examination alone. The department states that STATS 207 has no mid-semester test, and that its examination is the same paper as STATS 201 and 208.
- There is no mid-semester test — the department says so explicitly — so the first summative signal you receive is the assignment, and the project runs alongside everything else. The 45% examination threshold still applies, and because the paper is shared with STATS 201 and 208 it examines the standard data analysis syllabus rather than your project.
This is an exam-cram course. With the exams at 50% of the grade and the final examination alone at 50%, your result is overwhelmingly decided by how well you perform under time pressure. Dual pass: at least 45% required in this component alone.
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
- Distinguish types of investigation and state what each design supports.
- Design an investigation with operational definitions and a defensible sampling method.
- Explore and summarise data before modelling.
- Carry out inference for means and proportions and compare groups.
Before the final heaviest topics
- Fit and interpret simple and multiple regression models.
- Check model assumptions using residuals and diagnostics.
- Analyse categorical data and tests of association.
- Report an analysis stating clearly what the data do and do not support.
The mistakes that cost marks
Self-selected samples. Volunteers differ systematically from non-volunteers. Sample size does not fix selection bias, and often disguises it.
Ecological fallacy. Comparing group averages does not support a conclusion about individuals within those groups.
Variables not operationally defined. If two respondents can read the question differently, the resulting variable measures two different things.
Neglecting the shared examination. The project is engrossing and worth 30%. The examination is 50% and carries a 45% threshold.
Formula & concept sheet
The vocabulary and formulas you must own
- Operational definition
- A statement of exactly how a variable will be measured, so that different people measure the same thing.
- Observational study
- A design that measures variables as they occur, supporting association rather than causation.
- Experiment
- A design in which treatments are assigned, allowing causal conclusions.
- Selection bias
- Systematic difference between those included in a sample and the population it is meant to represent.
- Ecological fallacy
- Inferring individual-level relationships from group-level averages.
- Confounder
- A variable influencing both the presumed cause and the outcome, undermining a causal claim.
- Simple linear regression
- Fitting a straight-line relationship between one predictor and a response.
- Multiple regression
- Modelling a response from several predictors simultaneously.
- Residual
- The difference between an observed value and the value a model predicts; the basis of diagnostics.
- Effect size
- The magnitude of a relationship, distinct from whether it is statistically significant.
- Analysis of variance
- A procedure for comparing means across more than two groups.
- Dual pass requirement
- This course's rule that both an overall threshold and a separate final-examination threshold must be met.
Common acronyms: ANOVA · CI · SRS · UPI.
Where it fits
Prerequisites, related courses & why it matters
Prerequisite published by the department: 15 points from STATS 101, 108 or equivalent, together with the Stage I requirements for the 20x courses. Restriction: you may take only one of STATS 201, 207 and 208. The course is worth 15 points. The department lists Wild and Seber's Chance Encounters as the text and directs students to the Mathematics and Statistics Student Resource Centre.
Your STATS207 study toolkit
Study the course with Sia, not just read about it
Each tool already knows STATS207: 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 207 hard?
It rates moderately hard. There is no mid-semester test, which lowers the pressure relative to STATS 201 and 208, but the 30% group project is marked on design judgement and the 45% examination threshold still applies.
What is the assessment breakdown?
Final examination 50%, group project 30%, assignment 20%. You must obtain at least 50% overall and at least 45% in the final examination alone.
How does it differ from STATS 201 and 208?
The department states that STATS 207 has no mid-semester test and that its primary coursework assessment is a self-selected group project. The final examination is the same paper as STATS 201 and 208. You may take only one of the three.
What should I choose as a project?
A question narrow enough that you can define both variables operationally and actually collect the data. Ambition beyond the available data is the most common reason projects underperform.
What is the textbook?
The department lists Wild and Seber, Chance Encounters: A First Course in Data Analysis and Inference, and also directs students to the Mathematics and Statistics Student Resource Centre.
Does the project appear in the exam?
No. The examination is shared with STATS 201 and 208, so it examines the standard data analysis syllabus. The project is assessed separately.
Study STATS207 with Sia
Work through types of investigation, designing your own investigation, data collection 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
