MATH2801 Theory of Statistics
The Complete Exam Bible · T2 2026MATH2801 Overview
- UNSW Sydney
- Term 2, 2026
Within UNSW Sydney (the academic unit/school is NOT named anywhere in the verified course material — do not assert one), MATH2801 Theory of Statistics rebuilds probability into statistical theory in seven chapters — random variables and distribution functions, the common discrete and continuous distributions, bivariate distributions, how surveys and experiments actually generate data, the distribution of sums and averages (sampling distributions and the Central Limit Theorem), and finally estimators and their properties — with R/RStudio as the working environment from the Week 2 tutorial onwards.
This is a derivation course wearing a statistics label.
- MATH2801 grading 60% final exam, 30% pen-and-paper mid-term test (Week 7, in your tutorial class), 10% online statistics quiz in Möbius (Week 4)
- MATH2801 task mode Mid-term: in person, pen-and-paper, in your timetabled Week 7 tutorial, 50-minute limit. Bring your UNSW student ID card and a UNSW-approved calculator; you may bring ONE one-sided A4 HANDWRITTEN page of notes — If it's not handwritten or two-sided, your tutor will remove your notes. A summary table of common distributions is provided with the paper.
- MATH2801 mark trap The mid-term front-loads the risk: 30% of the course decided in 50 minutes, on one handwritten side of A4, over material the coordinator explicitly weights toward the newest chapters. You can expect more questions from Chapters 4, 5, and 6 in the test. So bivariate distributions, survey designs/experiments and the distribution of sums and averages carry the most marks in the shortest sitting, and the coordinator's own study advice is volume-based: I also recommend doing as many tutorial questions as you can, as questions will be of similar difficulty. There is no resit.
What you get in the full MATH2801 Exam Bible
- 8 chapters, 23 pages — every examinable topic
- 11 original practice questions, each with a model answer in the Final Exam format
- 8 worked examples, solved the way MATH2801 marks
- 15 computed figures, redrawn from the course’s own numbers
- Exam-morning plan for the Final Exam (60%) — what to revise last, where marks are lost
Free on this page: assessment table, chapter map, one worked example, key terms, FAQ. The rest is in the full exam bible.
How MATH2801 is assessed
| Component | Weight | Format |
|---|---|---|
| Online Statistics Quiz | 10% | Online quiz |
| Mid-term Test | 30% | Timed assessment |
| Final Exam | 60% | Final assessment |
The current Term 2 course page publishes a 10/30/60 assessment structure. Confirm the live quiz, test and Final Exam instructions in the course site and official timetable.
What other students are asking about MATH2801
- Where can I find lecture notes or study guides for MATH2801 at UNSW?
- The MATH2801 study guide in AskSia Library covers Theory of Statistics in 8 chapters, with the assessment table, a chapter-by-chapter topic map, key terms and a worked example, free to read on this page.
- Is there a final exam in MATH2801, and how much is it worth?
- Yes. In the offering this AskSia Library guide is built from, Final Exam carries 60% of the MATH2801 mark; the full split is Online Statistics Quiz 10%, Mid-term Test 30%, Final Exam 60%.
- What does MATH2801 cover on random variables and distribution functions?
- In AskSia Library's MATH2801 guide, the Random Variables and Distribution Functions chapter explains random variables · probability mass or density · cumulative distribution functions · move between event statements, support and distribution representations without losing inequalities.
- What does MATH2801 cover on common probability distributions?
- In AskSia Library's MATH2801 guide, the Common Probability Distributions chapter explains distribution families · parameters and support · moments and tail behaviour · match a random mechanism to a distribution before substituting into a formula.
- What does MATH2801 cover on bivariate distributions?
- In AskSia Library's MATH2801 guide, the Bivariate Distributions chapter explains joint distributions · marginal and conditional laws · covariance and independence · derive marginal and conditional information and test whether a relationship is merely uncorrelated or genuinely independent.
What MATH2801 covers
The learning path moves from Probability Review and Assessment Map, through the problems opened by Survey Designs and Experiments, to the synthesis required in R Workflow and Final-Exam Synthesis.
Probability Review and Assessment Map
sample spaces · conditional probability · Bayes reasoning · reconstruct the probability identities that later distribution and inference results depend onProbability Review and Assessment Map is a quantitative decision problem built from sample spaces, conditional probability and Bayes reasoning.
- sample spaces
- conditional probability
- Bayes reasoning
- Applying sample spaces
- Limits of conditional probability and Bayes reasoning
Random Variables and Distribution Functions
random variables · probability mass or density · cumulative distribution functions · move between event statements, support and distribution representations without losing inequalitiesRandom Variables and Distribution Functions is a quantitative decision problem built from random variables, probability mass or density and cumulative distribution functions.
- random variables
- probability mass or density
- cumulative distribution functions
- Applying random variables
- Limits of probability mass or density and cumulative distribution functions
Common Probability Distributions
distribution families · parameters and support · moments and tail behaviour · match a random mechanism to a distribution before substituting into a formulaCommon Probability Distributions is a quantitative decision problem built from distribution families, parameters and support and moments and tail behaviour.
- distribution families
- parameters and support
- moments and tail behaviour
- Applying distribution families
- Limits of parameters and support and moments and tail behaviour
Bivariate Distributions
joint distributions · marginal and conditional laws · covariance and independence · derive marginal and conditional information and test whether a relationship is merely uncorrelated or genuinely independentBivariate Distributions is a quantitative decision problem built from joint distributions, marginal and conditional laws and covariance and independence.
- joint distributions
- marginal and conditional laws
- covariance and independence
- Applying joint distributions
- Limits of marginal and conditional laws and covariance and independence
Survey Designs and Experiments
sampling frames · randomisation · bias and confounding · link the design mechanism to the population and causal claim the data can supportSurvey Designs and Experiments is a quantitative decision problem built from sampling frames, randomisation and bias and confounding.
- sampling frames
- randomisation
- bias and confounding
- Applying sampling frames
- Limits of randomisation and bias and confounding
Sums, Averages and Sampling Distributions
linear combinations · laws of expectation and variance · sampling distributions · derive the centre and spread of sums or averages before choosing an approximationSums, Averages and Sampling Distributions is a quantitative decision problem built from linear combinations, laws of expectation and variance and sampling distributions.
- linear combinations
- laws of expectation and variance
- sampling distributions
- Applying linear combinations
- Limits of laws of expectation and variance and sampling distributions
Estimators and Their Properties
estimators and estimates · bias and variance · consistency and efficiency · compare estimators by naming the target parameter and the loss or property relevant to the decisionEstimators and Their Properties is a quantitative decision problem built from estimators and estimates, bias and variance and consistency and efficiency.
- estimators and estimates
- bias and variance
- consistency and efficiency
- Applying estimators and estimates
- Limits of bias and variance and consistency and efficiency
R Workflow and Final-Exam Synthesis
simulation · analytic verification · interpretation and error checks · use R to test reasoning while preserving the derivation, assumptions and parameter-level conclusionR Workflow and Final-Exam Synthesis is a quantitative decision problem built from simulation, analytic verification and interpretation and error checks.
- simulation
- analytic verification
- interpretation and error checks
- Applying simulation
- Limits of analytic verification and interpretation and error checks
The lecturer's own 'Some revision and useful formulae' handout contains no statistics at all — it is integration by parts on ∫xe^(kx)dx, sums of arithmetic and geometric progressions including Σk·r^(k−1) = 1/(1−r)², the binomial theorem, Taylor series and the Gaussian integral ∫e^(−x²)dx = √π — because students are expected to derive means, variances and densities by hand.
And 90% of the mark is decided in two closed-window written sittings (a 50-minute pen-and-paper mid-term worth 30% and a 2-hour final worth 60%); only 10% comes from an online quiz that allows unlimited attempts.
Assessment in MATH2801 is distributed as follows: 60% final exam, 30% pen-and-paper mid-term test (Week 7, in your tutorial class), 10% online statistics quiz in Möbius (Week 4)
The operational assessment conditions matter here.
Mid-term: in person, pen-and-paper, in your timetabled Week 7 tutorial, 50-minute limit. Bring your UNSW student ID card and a UNSW-approved calculator; you may bring ONE one-sided A4 HANDWRITTEN page of notes — If it's not handwritten or two-sided, your tutor will remove your notes.
A summary table of common distributions is provided with the paper.
What makes MATH2801 demanding is concrete: The mid-term front-loads the risk: 30% of the course decided in 50 minutes, on one handwritten side of A4, over material the coordinator explicitly weights toward the newest chapters. You can expect more questions from Chapters 4, 5, and 6 in the test.
So bivariate distributions, survey designs/experiments and the distribution of sums and averages carry the most marks in the shortest sitting, and the coordinator's own study advice is volume-based: I also recommend doing as many tutorial questions as you can, as questions will be of similar difficulty. There is no resit.
Treat the MATH2801 hurdle status as unconfirmed.
Check the current official course outline for any component-level pass rule before relying on the overall mark.
For enrolment planning, Not stated in the verified course material (the Course Outline is an external LTI link that was not captured).
The course does assume prior probability: an O-Week 'Revision Chapter: Probability' is posted, and 'In the Week 1 tutorial, we will cover probability revision questions (please use the Probability Revision Notes above to brush up on some key concepts).'
The learning path moves from Probability Review and Assessment Map, through the problems opened by Survey Designs and Experiments, to the synthesis required in R Workflow and Final-Exam Synthesis.
Worked example · free
Worked example: Theory of Statistics integrated response
- 1Define the target quantity, population or reference condition represented by joint distributions.
- 1Write the operation or relationship required by simulation before substituting or simplifying.
- 1Carry the calculation or transformation through and use sampling frames as the interpretation check.
- 1Report the result with its unit, population or scope and enforce this limit: Large samples reduce random error but do not automatically remove selection bias or confounding.
Key terms
- Random variables and distribution functions
- A random variable maps outcomes to numbers, and its cumulative distribution function F(x) = P(X ≤ x) gives the probability that the variable does not exceed x.
- Common probability distributions (discrete and continuous)
- A probability distribution assigns probability to a random variable's possible values through a probability mass function for discrete variables or a density whose integral gives probability for continuous variables.
- Bivariate distributions
- A bivariate distribution gives joint probabilities for two random variables and determines their marginal, conditional and dependence structure.
- Survey designs and experiments
- A survey design selects units from a target population to estimate population features, while an experiment deliberately assigns treatments—ideally at random—to support causal comparison.
- Distribution of sums and averages / sampling distributions
- A sampling distribution is the probability distribution of a statistic over repeated samples; sums and averages inherit means and variances from their components, with covariance terms when observations are dependent.
- Central Limit Theorem
- The Central Limit Theorem states that, under suitable conditions, a standardised sum or sample mean approaches a normal distribution as sample size grows, regardless of the individual distribution's exact shape.
- Estimators and their properties
- An estimator is a rule for estimating an unknown parameter from sample data and is assessed through properties such as bias, variance, consistency and efficiency.
- Score and Fisher information
- The score is the derivative of the log-likelihood with respect to a parameter; Fisher information is its expected squared value, equivalently the negative expected second derivative under regularity conditions, and measures local parameter information.
MATH2801 FAQ
Is MATH2801 hard?
The mid-term front-loads the risk: 30% of the course decided in 50 minutes, on one handwritten side of A4, over material the coordinator explicitly weights toward the newest chapters. You can expect more questions from Chapters 4, 5, and 6 in the test.
So bivariate distributions, survey designs/experiments and the distribution of sums and averages carry the most marks in the shortest sitting, and the coordinator's own study advice is volume-based: I also recommend doing as many tutorial questions as you can, as questions will be of similar difficulty. There is no resit.
How is MATH2801 assessed?
60% final exam, 30% pen-and-paper mid-term test (Week 7, in your tutorial class), 10% online statistics quiz in Möbius (Week 4)
What is the MATH2801 exam or final-task format?
Mid-term: in person, pen-and-paper, in your timetabled Week 7 tutorial, 50-minute limit. Bring your UNSW student ID card and a UNSW-approved calculator; you may bring ONE one-sided A4 HANDWRITTEN page of notes — If it's not handwritten or two-sided, your tutor will remove your notes. A summary table of common distributions is provided with the paper.
Does MATH2801 have a hurdle or component-level pass rule?
Treat the MATH2801 hurdle status as unconfirmed. Check the current official course outline for any component-level pass rule before relying on the overall mark.
What prerequisites or restrictions apply to MATH2801?
Not stated in the verified course material (the Course Outline is an external LTI link that was not captured). The course does assume prior probability: an O-Week 'Revision Chapter: Probability' is posted, and 'In the Week 1 tutorial, we will cover probability revision questions (please use the Probability Revision Notes above to brush up on some key concepts).'
Is MATH2801 offered in Term 2, 2026?
This resource is aligned to Term 2, 2026. Confirm your class and assessment timetable in the current institutional system.
Is this MATH2801 resource an official university guide?
No. It is an independent MATH2801 study resource; current institutional instructions remain authoritative for assessment operation.
Questions students ask in each MATH2801 chapter
- What is the main task in Probability Review and Assessment Map?
- Reconstruct the probability identities that later distribution and inference results depend on. Chapter 01 · Probability Review and Assessment Map
- What is the main task in Random Variables and Distribution Functions?
- Move between event statements, support and distribution representations without losing inequalities. Chapter 02 · Random Variables and Distribution Functions
- What is the main task in Common Probability Distributions?
- Match a random mechanism to a distribution before substituting into a formula. Chapter 03 · Common Probability Distributions
- What is the main task in Bivariate Distributions?
- Derive marginal and conditional information and test whether a relationship is merely uncorrelated or genuinely independent. Chapter 04 · Bivariate Distributions
- What is the main task in Survey Designs and Experiments?
- Link the design mechanism to the population and causal claim the data can support. Chapter 05 · Survey Designs and Experiments
- What is the main task in Sums, Averages and Sampling Distributions?
- Derive the centre and spread of sums or averages before choosing an approximation. Chapter 06 · Sums, Averages and Sampling Distributions
- What is the main task in Estimators and Their Properties?
- Compare estimators by naming the target parameter and the loss or property relevant to the decision. Chapter 07 · Estimators and Their Properties
- What is the main task in R Workflow and Final-Exam Synthesis?
- Use r to test reasoning while preserving the derivation, assumptions and parameter-level conclusion. Chapter 08 · R Workflow and Final-Exam Synthesis
How to study for the exam
Retrieve the course map, practise the recurring method—identify the random object and support, derive the distribution or estimator, check regularity assumptions, compute transparently and interpret in parameter language—on changed scenarios, and verify every operational assessment detail in the live institutional system.
Your AI Statistics tutor for MATH2801
Stuck on a hard MATH2801 question? Sia is AskSia’s AI Statistics tutor — ask any MATH2801 Theory of Statistics question and get a clear, step-by-step explanation grounded in how the course is actually taught and assessed. Read this whole study guide free, then take your hardest questions to Sia.