ECON20003: pass the exams, not just read the notes
Your complete guide to University of Melbourne's quantitative methods 2 unit. See where the marks are, work real practice questions, and study with an AI tutor that knows ECON20003.
Sia generates ECON20003 practice questions, works through them step by step, and quizzes you on the material the exam weights most heavily.
Worked example
In an OLS regression (large sample) a slope coefficient has estimate 0.42 with standard error 0.15. Testing H0: beta = 0 at the 5% level (critical value approximately 1.96), what do you conclude?
The t-statistic is the estimate divided by its standard error: t = 0.42 / 0.15 = 2.8.
Since 2.8 > 1.96, reject H0 at the 5% level: the slope is significantly different from zero.
The R-squared measures fit, not the significance of an individual coefficient, so it is not needed for this test.
The trap: Dividing the standard error by the coefficient (giving about 0.36) or thinking the R-squared is needed. The t-statistic is the coefficient over its standard error, and it alone decides significance for that coefficient. classic slip!
One exam decides 50% of your grade. YES. This whole page is built around that.
Overview
What ECON20003 is, and where it sits
ECON20003 Quantitative Methods 2 (QM2) is the University of Melbourne's second-year quantitative-methods and econometrics subject, following first-year QM1. It builds the statistical-inference and regression toolkit that later economics, finance and econometrics subjects assume: sampling distributions and estimation, hypothesis testing, analysis of variance, simple and multiple regression, time-series ideas, and qualitative-response models such as logit and probit, with applied analysis carried out in R.
The emphasis is applied statistical reasoning under exam conditions plus regular hands-on assignments. The 50% closed-book final and the in-person mid-semester test reward fluent, correct inference and interpretation, while four spread assignments and weekly homework quizzes keep the applied R work continuous across the semester.
Official outline: handbook.unimelb.edu.au · ECON20003 outline. Always treat the official outline and the exam timetable as authoritative.
Difficulty & time commitment
Is ECON20003 hard, and how much time does it take?
ECON20003 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 unit.
Is this unit for you
Who tends to do well, and who tends to struggle
You will likely do well if
- You are comfortable with algebra and statistical notation and willing to drill inference until it is automatic.
- You keep the weekly R homework current, since the applied work compounds across the semester.
- You can interpret output, not just compute it: what a coefficient, t-statistic or p-value means in context.
You may struggle if
- You fall behind in the inference block; regression and the later models build directly on hypothesis testing.
- You treat R as a black box instead of understanding the statistics it produces.
- You under-practise the closed-book final, which rewards fast, correct hand inference and interpretation.
- Build a formula-and-interpretation sheet: t-statistic, confidence interval, R-squared, F-test, and what each says.
- Practise reading regression output and stating the conclusion in words, since interpretation carries marks.
- Work past exam questions by hand and timed, especially multi-step regression and ANOVA problems.
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 · Estimation & Hypothesis Testing of a Population Mean
The sampling distribution of the mean, Z vs t, confidence intervals and the five-step test
T2 · Normality & Nonparametric One-Sample Tests
Q-Q plots and Shapiro-Wilk, and the sign and Wilcoxon signed-rank tests when normality fails
T3 · Comparing Two Population Central Locations
Paired vs independent designs, pooled vs Welch t, and the rank-based alternatives
T4 · Inferences on Variances & Proportions (χ², t, F)
The chi-square, t and F distributions, the variance-ratio F-test and proportion tests
T5 · One-Way ANOVA & Nonparametric Alternatives
The sum-of-squares partition, F = MST/MSE, and the Kruskal-Wallis alternative
T6 · Correlation & Simple Linear Regression
Covariance and correlation, the OLS slope, its t-test, R² and prediction intervals
T7 · Multiple Regression, the General F-test & Specification
Partial effects, overall and partial F-tests, adjusted R² and multicollinearity/VIF
T8 · Heteroskedasticity & Dummy Independent Variables
Breusch-Pagan/White tests, robust standard errors, and indicator/interaction regressors
T9 · Dummy Dependent-Variable Models: LPM, Logit & Probit
The linear-probability model versus logit and probit, and marginal effects
T10 · Cross-Validation, Ridge & LASSO Regression
The bias-variance trade-off, k-fold cross-validation, and ridge versus LASSO shrinkage
T11 · Regression with Time-Series Data & Autocorrelation
Distributed-lag and autoregressive models, the Durbin-Watson test and the Newey-West remedy
T12 · Stationarity, Spurious Regression & the Dickey-Fuller Test
Weak stationarity, the spurious-regression trap and the (augmented) Dickey-Fuller unit-root test
How it's assessed
Assessment structure
| Component | Weight | Format & timing |
|---|---|---|
| First Assignment (individual or group of 2-4) | 10% | Quantitative analysis using a calculator and/or R/RStudio; typed solutions plus R code/printouts uploaded to Canvas as a single PDF; due 10am Mon 30 Mar (Week 5). |
| Mid-semester test (individual) | 10% | In-person, Wilson Hall (details TBA); held Fri 17 Apr. |
| Second Assignment (individual or group of 2-4) | 10% | As Assignment 1; due 10am Mon 4 May (Week 9). |
| Third Assignment (individual or group of 2-4) | 10% | As Assignment 1; due 10am Mon 18 May (Week 11). |
| Tutorial participation & homework exercises (individual) | 10% | Weekly Canvas Homework Quizzes; one mark per week for attending + participating AND submitting the prior week's homework by 10am Wed, on at least 10 weeks. |
| End-of-semester exam (individual) | 50% | Closed-book, in-person; 2h writing + 15 min reading; THREE long-answer questions each with several tasks, covering all 12 weeks; a formula sheet identical to the Canvas one plus statistical tables (z, t, χ², F, Wilcoxon/Durbin-Watson) are provided; an approved Casio FX-82 calculator (any suffix). HURDLE: you must pass the exam to pass the subject. YES. |
- Pass on a weighted average of at least 50%. No single-component hurdle unless noted; confirm against the official subject page.
This is an exam-cram unit. With the exams at 60% of the grade and the end-of-semester exam (individual) alone at 50%, your result is overwhelmingly decided by how well you perform under time pressure. YES.
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
Before the final heaviest topics
- Prioritise regression and inference, the core of the closed-book final.
- Rehearse the t-test, confidence intervals, ANOVA and the F-test until the mechanics are automatic.
- Practise interpreting output in words, not just computing statistics.
- Work past finals by hand and timed, including the logit/probit and time-series topics.
The mistakes that cost marks
Treating R as a black box. The exams test the statistics, not the software. Running R without understanding the inference leaves you unable to interpret or hand-compute under exam conditions.
Falling behind in inference. Regression, ANOVA and the qualitative-response models assume fluent hypothesis testing; a gap early compounds through the steep back half.
Computing without interpreting. Marks come from stating what a coefficient or test means in context. A correct number with no interpretation earns only part of the credit.
Teaching team
Who teaches ECON20003
The bios below are factual. We do not rate lecturers; any star ratings are submitted by students who have taken ECON20003.
Dr Mehmet Ozmen
Coordinates and lectures Quantitative Methods 2 in the Faculty of Business and Economics, University of Melbourne.
Associate Professor Victoria Baranov
Associate Professor of economics in the Faculty of Business and Economics, University of Melbourne.
Dr Emma Seyoum-Tegegn
Lecturer in the Faculty of Business and Economics, University of Melbourne.
Teaching team as listed in the unit materials reviewed. AskSia does not rate lecturers; star ratings are submitted by students who have taken ECON20003.
Formula & concept sheet
The vocabulary and formulas you must own
- t-statistic
- t = (estimate − hypothesised value) / standard error. For a slope, t = coefficient / its standard error; compare |t| to the critical value to test significance.
- Confidence interval
- estimate +/- (critical value × standard error): a range of plausible values for the parameter at a chosen confidence level.
- R-squared
- The proportion of variation in the dependent variable explained by the model. It measures fit, not the significance of any single coefficient.
- F-test
- Tests the joint significance of a group of coefficients (or overall regression) by comparing explained to unexplained variation.
- OLS slope
- The ordinary-least-squares estimate that minimises the sum of squared residuals; interprets as the change in the dependent variable per unit change in the regressor, holding others constant.
- Logit / probit
- Models for a qualitative (binary) outcome where the probability is a nonlinear function of the predictors, used when the dependent variable is 0/1 rather than continuous.
Common acronyms: OLS · CI · ANOVA · df · p-value · H0 · logit · probit.
Where it fits
Prerequisites, related units & why it matters
Second-year subject following first-year Quantitative Methods 1 (QM1) or equivalent; prerequisite-gated. Check the UniMelb Handbook for the exact sequence.
Your ECON20003 study toolkit
Study the unit with Sia, not just read about it
Each tool already knows ECON20003: 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 ECON20003 (QM2) hard?
It is moderate-to-hard because it is technical and exam-heavy: 60% of the grade is exams and the content is dense statistics and econometrics (regression, ANOVA, time series, logit/probit) with applied work in R. Consistent weekly practice makes it very manageable.
How is QM2 assessed?
Three assignments worth 10% each, a 10% in-person mid-semester test, 10% tutorial participation and weekly homework quizzes, and a 50% closed-book end-of-semester exam. The components sum to 100%.
How much maths and stats is involved?
A lot: sampling distributions, hypothesis testing, confidence intervals, simple and multiple regression, ANOVA, time-series ideas and qualitative-response models, with applied analysis in R.
Do I use software?
Yes, R is used for the applied assignments and homework, but the exams reward understanding and hand inference, so treat R as a tool rather than a black box.
What background do I need?
First-year quantitative methods (QM1 or equivalent) and comfort with algebra. The subject is prerequisite-gated and builds directly on first-year statistics.
Study ECON20003 with Sia
Work through the core topics 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