AB1202: ace the component, not just read the notes
Your complete guide to Nanyang Technological University's statistics & analysis course. See where the marks are, work real practice questions, and study with an AI tutor that knows AB1202.
Sia generates AB1202 practice questions, walks through counting methods; conditional probability and random variables step by step, and quizzes you on the material the component that weights most heavily.
Worked example
A random sample of 64 customer transactions has a mean value of $52 and a sample standard deviation of $12. Using the normal approximation with z = 1.96, what is the 95% confidence interval for the population mean transaction value?
The interval is built around the sample mean using the standard error of the mean, not the standard deviation of the data.
Margin of error = z × SE = 1.96 × 1.5 = 2.94.
Interval = 52 plus or minus 2.94, which is $49.06 to $54.94. Note how narrow it is compared with the spread of the data itself: that gap is the whole point of a sampling distribution.
The trap: Dividing by n instead of sqrt(n), which gives the implausibly tight interval $51.63 to $52.37. The other classic error is using s directly as if the interval described individual transactions rather than the mean, which produces $28.48 to $75.52. Both come from the same root confusion: a confidence interval describes the precision of an estimate of the mean, not the variability of the underlying data. classic slip!
One component decides 60% of your grade. The largest block of the course mark by a wide margin. It accumulates, so a weak run early cannot be recovered at the end. This whole page is built around that.
Overview
What AB1202 is, and where it sits
AB1202 is the statistics course in the Nanyang Business School first-year core, and it is structured around a single question: how do you infer something you cannot observe from data you can? Everything in the course is a step towards answering that with a stated level of confidence rather than a guess.
It runs as three modules. Module 1 builds the probability machinery: probability itself, conditional probability and independence, random variables and their distributions, and expectations. Module 2 is the inference core: sampling and sampling distributions, confidence intervals, and null hypothesis testing. Module 3 spends that machinery on two applications, linear regression with variable coding, and simulation analysis.
The distinguishing feature is that every weekly topic comes with a computer application in R. This is not an add-on: the course explicitly teaches basic programming so that students can run statistical analyses themselves and interpret the output, and 60% of the assessment is computer quizzes. Treating AB1202 as a pen-and-paper statistics course is the fastest way to lose marks in it.
Always treat your own course outline and the exam timetable as authoritative.
Difficulty & time commitment
Is AB1202 hard, and how much time does it take?
AB1202 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 willing to install R and work in it from Week 1, since 60% of the mark is assessed at the computer.
- You work steadily. Continuous assessment rewards weekly consistency and punishes catch-up attempts.
- You are comfortable with the idea that a statistic is itself random. That single shift, arriving around Week 6, unlocks the rest of the course.
- You read output critically rather than reporting whatever the software prints.
You may struggle if
- You plan to learn R the week before a quiz. The tool and the statistics are assessed together, so a tooling gap shows up as a statistics mark.
- You rely on a strong finish. There is no final examination to rescue a weak semester.
- You memorise formulas without their conditions. Confidence intervals and hypothesis tests are marked on interpretation as much as computation, and the standard misreadings are well known to markers.
- You treat probability weeks as warm-up. Modules 2 and 3 assume expectations and distributions are fluent.
- Write your own short R script for each weekly topic instead of running the supplied one. Being able to produce the analysis, not just follow it, is what the computer quizzes actually test.
- For every interval or test you compute, write one sentence stating what it does not mean. That habit catches the interpretation errors that separate a good mark from a top one.
- Rebuild the standard error from the sampling distribution once, by hand, so the sqrt(n) is a consequence rather than a rule you recall under time pressure.
- Start the group assignment during the regression weeks while the material is live, not after teaching ends.
Syllabus
The 15 topics, week by week
The exam-weight marker on each topic shows where the marks concentrate. The amber topics carry the highest exam weight.
W0 · Course briefing session
Sets out how the course runs and, more importantly, how it is assessed. Given that the assessment is continuous from early in the semester, the briefing is not a week to skip.
W1 · Probability basics
Module 1What a probability is and the rules it obeys. Everything downstream is an application of this, so fluency here pays compound interest.
W2 · Counting methods; conditional probability
Module 1Systematic counting, then conditioning: how the probability of an event changes once you know something else. Statistical independence is defined here and misused everywhere after.
W3 · Random variables and distribution functions
Module 1Moving from events to variables. Discrete and continuous random variables and the distribution functions that describe them.
W4 · Expectations
Module 1Expected value and variance as summaries of a distribution, and the algebra of expectations that later inference depends on.
W5 · Bivariate distributions and correlation
Module 1Two variables at once: joint behaviour, covariance and correlation. This is the bridge to regression later in the course.
W6 · Sampling distributions
Module 2The conceptual pivot of the course: a statistic computed from a sample is itself a random variable with its own distribution. Students who get this cleanly find the rest of Module 2 straightforward.
W7 · Central limit theorem
Module 2Why the normal distribution keeps appearing regardless of the population it came from, and what that licenses you to do with a large enough sample.
W8 · Confidence intervals
Module 2Attaching a stated level of confidence to an estimate. Interpretation is assessed as heavily as computation, and the two are commonly confused.
W9 · Null hypothesis statistical testing
Module 2Framing a claim as a testable hypothesis, choosing the test, and reading the result without overstating it.
W10 · Regression analysis I
Module 3Fitting and interpreting a linear relationship, including what the coefficients do and do not tell you.
W11 · Regression analysis II
Module 3Extending the model, including variable coding, and reading R output rather than hand-computed results.
W12 · Simulation analysis
Module 3Using the R environment to answer questions that are awkward analytically, by generating the distribution instead of deriving it.
W13 · Revision, no lesson
Self-directed consolidation week with no scheduled class.
W14 · Group assignment due
The group assignment falls due after teaching ends, so the work has to be scheduled during the weeks the quizzes are also running.
How it's assessed
Assessment structure
| Component | Weight | Format & timing |
|---|---|---|
| Individual participation | 10% | Individual. Across the semester. Assessed individually rather than as a group contribution. |
| Computer quizzes | 60% | Individual, conducted at the computer, consistent with the course's requirement that students run analyses in R and interpret the output. Repeated across the semester. The largest block of the course mark by a wide margin. It accumulates, so a weak run early cannot be recovered at the end. |
| E-learning and tests | 20% | Individual. Across the semester. Runs alongside the quiz series rather than replacing it. |
| Presentation | 10% | Assessed individually. Across the semester. Individual mark, even though the course also carries a group assignment. |
- No single-component hurdle is stated in the published course outline. Because 60% of the mark sits in a repeated quiz series, the practical pass condition is consistent weekly performance rather than a strong finish.
- There is no single final examination. The mark is assembled from a continuous quiz series, e-learning tests, a presentation and participation.
- Calculator policy: Not stated in the published course outline. The course is built around R, and the computer quizzes are conducted in that environment.
This is a coursework course. Coursework carries 100% of the grade and the computer quizzes is the single heaviest piece at 60%, so steady work across the semester decides your result more than any one sitting. The largest block of the course mark by a wide margin. It accumulates, so a weak run early cannot be recovered at the end.
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
- Conditional probability and independence, applied rather than recited
- Random variables, their distribution functions and expectations
- Bivariate distributions, covariance and correlation, including what correlation does not imply
- Basic R fluency: loading data, computing summaries, reading the output
Before the final heaviest topics
- Sampling distributions and the central limit theorem, explained in your own words
- Confidence intervals computed correctly and interpreted precisely
- Hypothesis testing: framing, choosing the test, and stating the conclusion without overclaiming
- Regression fitted and interpreted, including variable coding
- Simulation analysis set up and run in R
The mistakes that cost marks
Using s where the standard error belongs. The spread of the data and the precision of an estimate of the mean are different quantities. Dividing by sqrt(n) is what converts one into the other, and forgetting it is the single most common error in the inference weeks.
Reading a confidence interval as a probability about the parameter. The interval describes the procedure's long-run behaviour, not the chance that the parameter falls in this particular interval. Markers test the distinction directly.
Treating a non-significant result as proof of no effect. Failing to reject a null hypothesis is not evidence that it is true. Stating it that way loses marks even when the computation is correct.
Learning R by copying. Scripts that run when pasted do not survive a computer quiz where the data or the question has changed. Write the analysis yourself weekly, even when it is slower.
Formula & concept sheet
The vocabulary and formulas you must own
- Conditional probability
- The probability of an event given that another has occurred: P(A|B) = P(A and B) / P(B).
- Statistical independence
- Two events are independent when conditioning on one leaves the other's probability unchanged, so P(A and B) = P(A)P(B).
- Random variable
- A rule assigning a number to each outcome, so that a distribution can describe how those numbers behave.
- Expectation
- The probability-weighted average of a random variable, the distribution's centre of mass.
- Variance
- The expected squared deviation from the mean, measuring spread; its square root is the standard deviation.
- Covariance and correlation
- Covariance measures joint variation; correlation rescales it to between -1 and 1 so magnitudes are comparable.
- Sampling distribution
- The distribution of a statistic across repeated samples. The idea the whole of inference rests on.
- Standard error
- The standard deviation of a sampling distribution. For a sample mean it is s divided by the square root of n.
- Central limit theorem
- For a large enough sample, the sampling distribution of the mean is approximately normal regardless of the population's shape.
- Confidence interval
- An interval built by a procedure that captures the parameter a stated proportion of the time in repeated sampling.
- Null hypothesis
- The default claim a test is set up to challenge; the test asks whether the data are unusual under it.
- p-value
- The probability, if the null hypothesis holds, of data at least as extreme as what was observed.
- Linear regression
- Fitting a straight-line relationship between variables and interpreting the coefficients that describe it.
- Variable coding
- Representing categorical information numerically so it can enter a regression, and reading the coefficients that result.
- Simulation analysis
- Generating a distribution computationally instead of deriving it analytically, then reading the result.
Common acronyms: {'term': 'CI', 'def': 'Confidence interval'} · {'term': 'CLT', 'def': 'Central limit theorem'} · {'term': 'RV', 'def': 'Random variable'} · {'term': 'SE', 'def': 'Standard error'} · {'term': 'R', 'def': 'The statistical computing environment used throughout the course'} · {'term': 'AU', 'def': 'Academic Units, the NTU credit measure'} · {'term': 'ILO', 'def': 'Intended Learning Outcome'}.
Where it fits
Prerequisites, related courses & why it matters
No prerequisites are stated in the published course outline. AB1202 is itself listed as a prerequisite for later NTU analytics and computing courses, including the advanced predictive analytics and computer network courses in the business and computing curricula.
Your AB1202 study toolkit
Study the course with Sia, not just read about it
Each tool already knows AB1202: 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 AB1202 a programming course?
Partly. It teaches basic programming in R so that you can run statistical analyses and interpret the results, and every weekly topic comes with a computer application. The statistics is the subject; R is the tool you are assessed through.
How is AB1202 assessed?
Computer quizzes 60%, e-learning and tests 20%, individual participation 10%, presentation 10%. There is no single final examination, so the mark is built continuously through the semester.
Which week is the hardest?
The Week 6 to 7 stretch, where the course moves from describing distributions to reasoning about the distribution of a statistic. Students who get sampling distributions and the central limit theorem cleanly find confidence intervals and hypothesis testing follow naturally.
Can I catch up if I fall behind?
Less easily than in an exam-weighted course. With 60% of the mark in a continuous quiz series and no final to rescue the grade, missed weeks convert directly into lost marks rather than into a harder revision period.
Do I need statistics background before AB1202?
The outline states no prerequisites, and the course begins from probability basics. What helps most is comfort with algebra and a willingness to work in R from the first weeks rather than deferring it.
What is the group assignment?
The planned schedule places a group assignment due in Week 14, after teaching ends. Because the quiz series is running throughout the semester, it is worth scheduling that work early rather than leaving it to the final fortnight.
Study AB1202 with Sia
Work through counting methods; conditional probability, random variables, expectations 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
