ST2334: pass the exams, not just read the notes
Your complete guide to National University of Singapore's probability and statistics course. See where the marks are, work real practice questions, and study with an AI tutor that knows ST2334.
Sia generates ST2334 practice questions, walks through basic concepts of probability and conditional probability step by step, and quizzes you on the material the exam weights most heavily.
Worked example
A factory's bolts have lengths that are normally distributed with mean 50mm and standard deviation 2mm. What proportion of bolts are longer than 53mm? (Use P(Z > 1.5) = 0.0668.)
Standardise the value. Z = (X − mean) / standard deviation = (53 − 50) / 2 = 1.5. This converts the question to the standard normal.
Read the given value directly: P(Z > 1.5) = 0.0668. This is the upper-tail probability, exactly what the question asks for.
Sanity check the direction. 53mm is above the mean, so fewer than half the bolts exceed it; 0.0668 is well below 0.5, which is consistent. The complement 0.9332 would answer 'shorter than 53mm', which is option B and the standard wrong turn.
The trap: Reporting the complement 0.9332 because the standard normal table gives cumulative (less-than) probabilities. The question asks for the upper tail, so subtract from 1, or read the upper-tail value directly. Getting the tail direction wrong is the single most common error in every normal-distribution question in this course. classic slip!
One exam decides 70% of your grade. Open book. This whole page is built around that.
Overview
What ST2334 is, and where it sits
ST2334 is NUS's standard first course in probability and statistics, taken across Science and required in the Computer Science degree. Its official description is precise: the course introduces students to basic probability theory and statistical inference, with topics spanning basic concepts of probability, conditional probability, independence, random variables, joint and marginal distributions, mean and variance, some common probability distributions, sampling distributions, and estimation and hypothesis testing based on a normal population.
The course divides cleanly into two halves. The first is probability: how to quantify uncertainty, update it with conditioning, and describe it through random variables and their distributions. The second is inference: using a sample to say something about a population, through sampling distributions, point and interval estimation, and hypothesis testing.
Assessment is a 70% final examination and 30% online quizzes. The final is run open book, which NUS uses across several quantitative courses; this removes the need to memorise distribution formulas but leaves the actual skill — setting up and solving the problem correctly under time pressure — entirely intact.
Official outline: nusmods.com · ST2334 outline. Always treat the official outline and the exam timetable as authoritative.
Difficulty & time commitment
Is ST2334 hard, and how much time does it take?
ST2334 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 are fluent with calculus, since continuous distributions require integrating density functions.
- You always standardise before reading a normal probability, and you check the tail direction every time.
- You keep the probability half and the inference half as distinct toolkits, and know which one a question is testing.
- You build your open-book materials during the semester and practise with them, rather than assembling them the night before.
You may struggle if
- You memorise procedures without understanding what a sampling distribution is, which fails the entire inference half.
- You confuse the distribution of the data with the distribution of a statistic, the core idea of sampling distributions.
- You read cumulative-probability tables without tracking whether the question wants an upper or lower tail.
- You skip the low-stakes quizzes and make the 70% final carry everything.
- Build a one-page distribution card: for each named distribution, its parameters, mean, variance and the situation it models.
- For every normal-distribution problem, write the standardisation step explicitly. Most lost marks are tail-direction slips, not conceptual gaps.
- Learn hypothesis testing as a fixed procedure: state hypotheses, choose the statistic, find its null distribution, compute, compare, conclude. Executing it the same way every time removes errors.
- Practise past-paper questions under the open-book time constraint, using exactly the notes you plan to bring.
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 · Basic concepts of probability
Official course descriptionSample spaces, events, axioms of probability and counting.
T2 · Conditional probability and independence
Official course descriptionConditioning, the multiplication rule, total probability and Bayes' theorem.
T3 · Random variables
Official course descriptionDiscrete and continuous random variables, probability mass and density functions.
T4 · Mean, variance and expectation
Official course descriptionExpected value, variance, and the properties of expectation operators.
T5 · Joint and marginal distributions
Official course descriptionTwo-dimensional random variables, marginals, and conditional distributions.
T6 · Covariance and correlation
Standard probability canonMeasuring dependence between random variables and the independence-uncorrelatedness distinction.
T7 · Common discrete distributions
Official course descriptionBinomial, Poisson and geometric distributions and where each applies.
T8 · Common continuous distributions
Official course descriptionUniform, exponential and normal distributions, and standardising the normal.
T9 · Sampling distributions
Official course descriptionThe distribution of a statistic, the central limit theorem, and the t and chi-square distributions.
T10 · Point estimation
Official course descriptionEstimators, bias, and estimating a population mean and variance from a sample.
T11 · Interval estimation
Official course descriptionConfidence intervals for a normal mean, and interpreting them correctly.
T12 · Hypothesis testing
Official course descriptionNull and alternative hypotheses, test statistics, significance and errors, for a normal population.
How it's assessed
Assessment structure
| Component | Weight | Format & timing |
|---|---|---|
| Final examination | 70% | Open-book final examination covering the whole course. Hard or soft copies stored on the exam laptop are permitted. NUS examination period. Open book. |
| Online quizzes | 30% | Online quizzes across the semester. Across the semester. Continual assessment. |
- The two components sum to 100. No separate component hurdle is published.
- The final is open book and worth 70%, so distribution tables and formulas can be brought. The constraint is time and correct set-up, not recall. Because the quizzes are 30% of low-stakes continual work, keeping them current makes the final less decisive.
This is an exam-cram course. With the exams at 70% of the grade and the final examination alone at 70%, your result is overwhelmingly decided by how well you perform under time pressure. Open book.
Final exam timing: During the NUS examination period. 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 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
- Compute probabilities using the axioms, conditioning, total probability and Bayes' theorem.
- Work with discrete and continuous random variables, finding probabilities from mass and density functions.
- Compute expectation and variance, and apply their properties.
- Handle joint and marginal distributions and determine independence.
Before the final heaviest topics
- Apply the binomial, Poisson, exponential and normal distributions to the right situations.
- Standardise normal variables and read tail probabilities in the correct direction.
- Use the central limit theorem and identify sampling distributions including t and chi-square.
- Construct confidence intervals and carry out hypothesis tests for a normal population, interpreting the result.
The mistakes that cost marks
Reading the wrong tail. Standard normal tables give cumulative probabilities. For 'greater than', subtract from 1. This single slip accounts for most normal-distribution errors.
Confusing data with the statistic. Sampling distributions describe the behaviour of a statistic like the sample mean, not the raw data. The standard error is not the standard deviation.
Treating uncorrelated as independent. Independence implies zero correlation, but zero correlation does not imply independence. The course tests the distinction.
Misstating hypotheses. The null hypothesis carries the equality. Setting up the alternative in the wrong direction, or as the equality, invalidates the whole test.
Formula & concept sheet
The vocabulary and formulas you must own
- Conditional probability
- P(A given B) = P(A and B) / P(B), the probability of A once B is known to have occurred.
- Bayes' theorem
- A rule for reversing a conditional probability using the prior and the total probability of the evidence.
- Random variable
- A function assigning a number to each outcome, described by a probability mass function (discrete) or density function (continuous).
- Expectation
- The long-run average value of a random variable, the probability-weighted sum or integral of its values.
- Variance
- The expected squared deviation from the mean, measuring spread; its square root is the standard deviation.
- Binomial distribution
- The distribution of the number of successes in a fixed number of independent trials with constant success probability.
- Poisson distribution
- The distribution of the count of events in a fixed interval when events occur independently at a constant average rate.
- Normal distribution
- The symmetric bell-shaped continuous distribution defined by its mean and variance, standardised via the Z-score.
- Central limit theorem
- The result that the sample mean of many independent observations is approximately normal regardless of the underlying distribution.
- Sampling distribution
- The probability distribution of a statistic computed from a sample, such as the sample mean.
- Confidence interval
- A range constructed from sample data that contains the true parameter with a stated long-run frequency.
- Hypothesis test
- A procedure using a test statistic and its null distribution to decide between a null and alternative hypothesis at a chosen significance level.
Common acronyms: CLT · CDF · iid · PDF · PMF.
Where it fits
Prerequisites, related courses & why it matters
Prerequisite published on NUSMods: one of MA1102R, MA1312, MA1505, MA1507, MA1511, MA1521 or MA2002. Preclusions include ST1232, ST2131, MA2116, MA2216 and several others. ST2334 is worth 4 units and is required in the Computer Science degree.
Your ST2334 study toolkit
Study the course with Sia, not just read about it
Each tool already knows ST2334: 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 ST2334 hard?
It rates moderately hard. The material is a standard first course, but it is relentlessly quantitative and the two halves — probability then inference — each have their own machinery. The 70% open-book final rewards accurate set-up rather than memorisation.
What is the assessment breakdown?
70% final examination and 30% online quizzes. The final is open book: hard or soft copies of your materials on the exam laptop are permitted.
What can I bring to the open-book final?
Your own notes and formula sheets, in hard copy or stored on your exam laptop. That removes memorisation of distribution formulas, but the paper is time-constrained, so a well-organised cheat sheet you have actually practised with is worth more than a comprehensive one you have not.
What are the prerequisites?
One of a list of first-year calculus courses: MA1102R, MA1312, MA1505, MA1507, MA1511, MA1521 or MA2002. You need the calculus to handle continuous distributions and integration of density functions.
Why is it required for Computer Science?
Probability and statistical inference underpin algorithms analysis, machine learning and data-driven systems. ST2334 is the common statistical foundation the Computer Science degree builds on.
What is the hardest part?
For most students it is the transition from probability to inference, and specifically sampling distributions and hypothesis testing, where you reason about the distribution of a statistic rather than of the data. Getting the tail direction and the correct test right under time pressure is where marks are lost.
Study ST2334 with Sia
Work through basic concepts of probability, conditional probability, random variables 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
