26134: pass the exams, not just read the notes
Your complete guide to University of Technology Sydney's responsible evidence-based decisions unit. See where the marks are, work real practice questions, and study with an AI tutor that knows 26134.
Sia generates 26134 practice questions, walks through estimating values for the population and testing ideas step by step, and quizzes you on the material the exam weights most heavily.
Worked example
A customer wins a single play of a game with probability p = 0.2, independently each time. They play n = 5 times, so the number of wins X follows a binomial distribution, X ~ Bin(5, 0.2). What is the probability of exactly 2 wins, P(X = 2)?
The binomial probability is P(X = k) = C(n, k) p^k (1 − p)^(n − k), where C(n, k) is the number of ways to choose k successes from n trials.
Multiply: P(X = 2) = 10 × 0.04 × 0.512 = 0.2048, which rounds to 0.205 (option index 1). This matches the binomial table entry Pr(X = 2; 5, 0.2) = 0.205.
The trap: 0.942 is P(X <= 2), the cumulative probability of at most 2 wins, which you read straight off a cumulative binomial table. The question asks for exactly 2 wins, P(X = 2), which is a single mass-function value. Confusing 'exactly' (the PMF) with 'at most' or 'at least' (the CDF) is the most common discrete-distribution error, and 0.410 is P(X = 1), the single most likely outcome, which tempts a quick guess. classic slip!
One exam decides 50% of your grade. Covers the whole subject. The exam is worth 50% and stays within the lecture notes. This whole page is built around that.
Overview
What 26134 is, and where it sits
26134 Responsible Evidence-Based Decisions is the UTS Business School's first-year statistics and data-analysis core: a 6-credit-point subject that introduces probability theory, applied statistics and data analysis with a focus on hands-on application. It is a core component of the Bachelor of Business, the Bachelor of Economics and a range of joint degrees, and its stated goal is to train you to be a responsible user of data, able to describe the world (descriptive statistics) and to draw inferences about it (inferential statistics) for business decision-making.
The content is organised into five modules that build cumulatively: Module 1 (descriptive statistics and data communication), Module 2 (inferential statistics and sampling), Module 3 (hypothesis testing), Module 4 (regression analysis) and Module 5 (data ethics). The early weeks cover exploring and communicating data and the foundations of probability; the middle weeks move to discrete and continuous distributions, sampling distributions, confidence intervals and hypothesis testing; the back end adds regression and a self-contained ethics module. Because each week's lecture depends on the previous one, the subject coordinator's explicit advice is that catching up after falling behind is very hard.
Delivery is online and on campus: live Zoom lectures on Mondays (recorded to Canvas) plus mostly face-to-face tutorials that start in Week 2 and run one week behind the lecture. The lecture notes are described as self-contained and the only required reference, so all assessment (quizzes, group assignment and final exam) stays within the lecture material. A recommended Business Analytics and Statistics textbook (Black et al.) supports extra practice but is not required, and statistical tables (Z, t, chi-square, F and binomial) plus Excel are the working tools throughout.
Difficulty & time commitment
Is 26134 hard, and how much time does it take?
26134 is manageable if you keep a weekly rhythm and treat the back half as the main event. Across student reviews the pattern is consistent: it starts gently and steepens, and the heaviest assessment is the part that separates grades.
A read across student reviews and course feedback. See what students say ↓
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 unit.
Is this unit for you
Who tends to do well, and who tends to struggle
You will likely do well if
- You keep pace with the weekly lectures from Week 1, because each topic builds on the previous one and the coordinator's own warning is that catching up after falling behind is very hard.
- You attempt the tutorial questions by hand before the tutorial and self-mark, rather than only reading the brief posted solutions.
- You build instant recognition of which distribution or test applies (binomial versus normal, Z versus t versus chi-square versus F) and which statistical table to reach for.
- You are comfortable in Excel and practise the table lookups, since the restricted-open-book exam rewards speed and fluency, not having the notes.
You may struggle if
- You assume high-school maths covers it; statistics ideas differ from calculus and algebra, and the false confidence shows up once distributions and inference arrive.
- You let the cumulative modules pile up and try to cram inference, hypothesis testing and regression in the last weeks.
- You treat the open-book exam as a reason not to revise; with 25 timed questions and no internet, hunting through notes for the right test is too slow.
- You memorise formulas without practising the table lookups and Excel steps, so the mechanical parts cost you time and accuracy under pressure.
- Keep a one-page decision tree for choosing the right test statistic and critical value (Z, t, chi-square, F), and rehearse using it until the choice is automatic.
- Drill the statistical-table lookups and the matching Excel functions so the mechanics are instant in the restricted-open-book exam.
- Work the Autumn 2025 practice exam and the sample questions timed, including the data-communication and data-ethics topics that earlier past papers did not cover.
- Sit each quiz seriously as a checkpoint; they are your clearest signal of whether you have kept pace before the 50% final.
Syllabus
The 12 topics, week by week
The exam-weight marker on each topic shows where the marks concentrate. The amber topics carry the highest exam weight.
W1 · Exploring data (descriptive statistics)
Module 1Descriptive statistics: measures of centre and spread, the shape of distributions, skewness and correlation, and how to summarise a real dataset (a class Netflix survey is used in lectures).
W2 · Communicating insights from data
Module 1Turning numbers into a message: exploratory versus explanatory framing, visual-perception principles, scatterplots, why to include zero on the y-axis, the pitfalls of pie charts and misleading or dishonest charts.
W3 · Predicting events (probability)
Module 2Foundations of probability: sample spaces and events, contingency tables, marginal, joint and conditional probabilities, Venn diagrams, mutually exclusive and independent events, and a brief look at Bayes' rule.
W4 · Predicting events when outcomes are discrete
Module 2Discrete random variables: the probability mass function and cumulative distribution function, the mean, variance and standard deviation of a distribution, and the binomial, Bernoulli and discrete-uniform distributions (with the binomial table).
W5 · Predicting events when outcomes are continuous
Module 2Continuous random variables: why a single point has probability zero, area-under-the-curve probabilities, and the normal distribution with standardisation and the Z table.
W6 · Insights from limited information (sampling)
Module 2Drawing inferences from a sample rather than the whole population: sampling distributions, the standardised sample mean as a random variable and the role of the central limit theorem.
W7 · Estimating values for the population
Module 2Confidence intervals for the mean using Z (known variance) and t (unknown variance), and for the variance and standard deviation using chi-square; what a confidence level does and does not mean.
W8 · Testing ideas and interventions I (hypothesis testing)
Module 3The logic of hypothesis testing: null and alternative hypotheses, test statistics and critical values, p-values, significance levels, and Type I and Type II errors, using the decision tree to pick the right test.
W9 · Testing ideas and interventions II
Module 3Comparing groups: the two-independent-sample and paired t-tests, ANOVA for more than two groups, and the F-test for differences in variances.
W10 · Modelling relationships with regression
Module 4Simple and multiple linear regression: fitting a line, interpreting coefficients and isolating the effect of one factor while holding others fixed, the counterfactual interpretation, and basic model fit.
W11 · Ethical use of data
Module 5Data ethics: rules versus principles, the four ethical principles (respect for persons, beneficence, justice, respect for law and public interest), consequentialist and deontological frameworks, anonymisation and the Five Safes framework.
W12 · Review and exam preparation
All modulesConsolidation across all five modules, working past papers and sample questions, and practising the restricted-open-book exam format under timed, table-and-Excel conditions.
How it's assessed
Assessment structure
| Component | Weight | Format & timing |
|---|---|---|
| Online quizzes (6) | 30% | Six Canvas quizzes across the semester, each covering the preceding weeks' lecture topics; no AI permitted. Quizzes roughly in Weeks 3, 5, 7, 9, 11 and 12 (dates subject to change). Continuous-assessment cushion. Indicative split: the quizzes and group assignment make up the non-exam 50%; confirm the exact per-component weights against the official Subject Outline. |
| Group assignment | 20% | Applied group data project; limited use of AI permitted within the assignment instructions. Due around Week 11 (date subject to change). Indicative weight: the quizzes plus group assignment make up the non-exam 50%; confirm the exact split against the official Subject Outline. |
| Final exam | 50% | Restricted open book, 120 minutes, online via ProctorU: 25 questions presented all at once, each worth the same marks; calculator of any type, Excel, Word and PDF notes and all paper-based notes permitted; cloud-stored notes and the internet are not accessible; no AI. Formal exam period (Autumn results published 29 June for the Autumn offering). Covers the whole subject. The exam is worth 50% and stays within the lecture notes. |
- Pass on a weighted average of at least 50%. No single-component hurdle is stated in the materials reviewed; attendance is not assessed.
- Final exam: 25 questions presented all at once, each worth the same marks, in a single 120-minute ProctorU sitting. It is restricted open book, so the marks reward speed and table-and-Excel fluency: knowing instantly which distribution or test applies matters more than having the notes.
- Calculator policy: Final exam: a calculator of any type is permitted, along with Excel, Word and PDF notes and all paper-based notes (lecture notes, textbook, tutorial exercises, practice exams). Notes stored on the cloud and the internet are not accessible.
This is an exam-cram unit. With the exams at 50% of the grade and the final exam alone at 50%, your result is overwhelmingly decided by how well you perform under time pressure. Covers the whole subject. The exam is worth 50% and stays within the lecture notes.
Final exam timing: approx Nov 2026 (Spring offering, confirm against the official exam timetable). Confirm the exact date and venue on the official exam timetable.
How to actually pass it
A weekly rhythm, two checklists, and the traps to avoid
The unit 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
- Lock in Module 1 and 2 basics: descriptive statistics, probability rules, contingency tables, and the binomial, normal and sampling distributions, before the quizzes that gate them.
- Practise reading the Z and binomial tables until lookups are instant.
- Make sure you can build a confidence interval for the mean using both Z (known variance) and t (unknown variance).
- Sit each early quiz seriously to calibrate, since they are your main feedback signal before the final.
Before the final heaviest topics
- Build and rehearse a decision tree for hypothesis testing: which test statistic and critical value apply to a mean, a variance, a difference in means (independent or paired), more than two groups (ANOVA) or two variances (F-test).
- Work the Autumn 2025 practice final and the sample questions timed, then check method, not just the answer, including the data-communication and data-ethics questions.
- Prepare a clean, downloaded folder of notes, formula sheet, tables and Excel files before the ProctorU sitting, since the internet and cloud notes are not accessible.
- Drill regression interpretation and the Excel output (coefficients, fit and the isolated effect of one variable), and rehearse the data-ethics frameworks for the conceptual questions.
The mistakes that cost marks
Confusing 'exactly' with 'at most' or 'at least'. For a discrete distribution, P(X = k) is a single mass-function value while P(X <= k) is the cumulative total. Reading the wrong column of the binomial or Z table, or summing when the question wants one value, is the most common distribution error and it cascades into wrong probabilities and wrong test conclusions.
Falling behind on a cumulative subject. Each week's lecture depends on the previous one, and the coordinator states plainly that catching up is very hard. Letting Module 2 or 3 slide makes confidence intervals, hypothesis testing and regression feel impossible in the last weeks.
Treating open book as no-revision. The exam is restricted open book, but it is 25 timed questions with no internet. Students who plan to look everything up run out of time. The notes are a safety net for a formula, not a substitute for knowing which test to run.
Picking the wrong test statistic. Choosing Z when the population variance is unknown (it should be t), or reaching for a t-test when the question is about variances (F) or more than two groups (ANOVA), is a recurring trap. The hypothesis-testing decision tree exists precisely to stop this.
Teaching team
Who teaches 26134
The bios below are factual. The star ratings are not ours: they are impressions from students who have taken the unit, so you can hear from people who sat in the lectures.
Nathan Kettlewell
Associate professor in the Economics Department at the University of Technology Sydney, with research interests in public policy, health economics and behavioural economics; coordinates and lectures 26134.
Teaching team as listed in the unit materials reviewed. AskSia does not rate lecturers; star ratings are submitted by students who have taken 26134.
What students say
What students actually say about 26134
Recurring themes from student reviews, paraphrased in our own words.
- Described as cumulative: each week builds on the last, so falling behind on the early probability and distribution material makes the inference weeks much harder.
- Statistics ideas feel different from high-school calculus and algebra; students with weaker maths lean on the free Math Refresher sessions and U:PASS.
- Manageable with consistent weekly practice, table fluency and comfort in Excel.
- The lecture notes are the single self-contained reference, and students build a personal formula-and-table sheet to download into their exam notes folder.
- Past papers (the Autumn 2025 practice final and sample questions) and the hypothesis-testing decision tree are the core revision tools.
- Demand for timed practice on choosing the right distribution and test under the restricted-open-book, no-internet ProctorU format.
Recurring student opinions, paraphrased and aggregated, not official course information.
Set texts
The prescribed reading
The syllabus references map straight onto these.
Business Analytics and Statistics
Ken Black, John Asafu-Adjaye, Paul Burke, Nazim Khan, Gerard King, Nelson Perera, Andrew Papadimos, Carl Sherwood, Saleh Wasimi. ISBN 9781394189670. Publisher page
Where it fits
Prerequisites, related units & why it matters
A first-year core subject with no listed prerequisite. How hard it feels depends on your maths background; the unit offers free 'Math Refresher' drop-in sessions (around Weeks 1 and 4) to bring basic maths up to speed, and a U:PASS peer-study option.
Your 26134 study toolkit
Study the unit with Sia, not just read about it
Each tool already knows 26134: 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 26134 hard?
It is moderate for a first-year subject. The early weeks (descriptive statistics, data communication and basic probability) are gentle, but the unit builds cumulatively into distributions, confidence intervals, hypothesis testing and regression, and the coordinator warns that statistics ideas differ from high-school maths and that catching up after falling behind is very hard. Keeping pace with the weekly lectures and doing the tutorial questions makes it very manageable.
How is 26134 assessed?
Continuous assessment of six online quizzes plus a group data project, and a 50% final exam. The non-exam half is split between the quizzes and the group assignment; confirm the exact per-component weights against the official Subject Outline. You pass on a weighted average of at least 50%, with no single-component hurdle stated in the materials reviewed.
What is the final exam format?
A restricted-open-book online exam of 120 minutes via ProctorU, worth 50%. There are 25 questions presented all at once, each worth the same marks. A calculator of any type, Excel, Word and PDF notes and all paper-based notes are permitted, but cloud-stored notes and the internet are not accessible and AI is not allowed. Download every note you want into a local folder before you start.
How much maths is involved?
It is applied statistics rather than proof-heavy maths: probability rules, discrete and continuous distributions, reading statistical tables (Z, t, chi-square, F and binomial), confidence intervals, hypothesis tests and regression, with plenty of Excel. A calculator is permitted in the exam. Free Math Refresher drop-in sessions are offered early in the semester for anyone whose maths is rusty.
Do I need to buy the textbook?
No. The lecture notes are described as self-contained and the only required reference, and all assessment stays within them. Business Analytics and Statistics by Black et al. (1st or 2nd edition) is recommended for extra practice and is available as a restricted library e-book, but it is optional.
Can I use AI or a calculator in this subject?
You can use generative AI in your own preparation (for example to generate practice questions or explanations), and limited AI is allowed in the group assignment within the assignment instructions. AI is not permitted in the in-class quizzes or the final exam. A calculator of any type is allowed in the final exam, along with Excel and your downloaded notes.
Study 26134 with Sia
Work through estimating values for the population, testing ideas, testing ideas and the rest of the unit with a tutor that knows it and quizzes you on the topics the assessments weight most heavily.
Start studying with Sia