ECON90033 Quantitative Analysis of Finance I
The Complete Exam Bible · S2 2026ECON90033 Overview
- Graduate coursework
- Semester 2, 2026
- Financial econometrics
- R programming
Quantitative Analysis of Finance I study route
Quantitative Analysis of Finance I is mapped from the current Semester 2, 2026 teaching sequence. The 6 chapters follow the evidence available for this offering, with deeper pages assigned to topics carrying more calculation, comparison or boundary work.
- Transform data deliberately Returns, differences and trends answer different questions.
- Diagnostics are part of modelling Residuals, stability and forecast errors control interpretation.
- The examination is a hurdle A passing examination result is required by the Subject Guide.
- Diagnose before trusting forecasts Write the information set, model assumption and diagnostic result beside every forecast before interpreting its financial meaning.
How ECON90033 is assessed
| Component | Weight | Format |
|---|---|---|
| In class participation | 5% | Individual participation from Week 1 to Week 12 |
| Quiz (weekly, 250 words) | 5% | Individual weekly quiz activity |
| First Assignment | 15% | Individual or pair assignment |
| Second Assignment (individual or pair) | 25% | Individual or pair assignment |
| 2-hour end-of-semester exam (individual) · hurdle | 50% | Individual end-of-semester examination |
The current Subject Guide publishes five weighted components totalling 100% and states that the end-of-semester examination must be passed.
Assessment structure
Segment widths reproduce the published percentage weights and total 100%.
What ECON90033 covers
Six chapters progress from returns and regression to time-series, volatility and multivariate models.
Financial Prices, Returns and Data Properties
Transform price observations into returns and inspect their distribution02Linear Regression and CAPM Evidence
Estimate conditional relationships and separate fit from economic interpretation03Portfolio Performance and Multifactor Models
Connect portfolio weights, risk exposure and performance measures04Autocorrelation and ARMA Forecasting
Model temporal dependence and preserve the forecast information set05Trends, Unit Roots and Spurious Regression
Distinguish deterministic trend, stochastic trend and stationary movement06Conditional Volatility, VAR and Cointegration
Extend the toolkit to changing variance and multivariate dynamicsBegin with the published assessment table, select the chapter that matches the task, retrieve the governing concepts, complete a changed case and verify the final claim.
The recurring method is define the data-generating object, specify the model, estimate or calculate transparently, diagnose assumptions and interpret at the supported horizon.
Definitions, worked explanations, numerical checks and diagrams serve that method. Practice cases are written for study and are not official questions or marking schemes.
Current dates, submission settings and permitted resources remain controlled by the University learning system and timetable.
Financial Prices, Returns and Data Properties
The opening lectures introduce financial prices, simple and log returns, descriptive statistics and statistical properties.
Use this chapter to convert prices to simple and log returns, then interpret scale, sign and distributional evidence Keep A return transformation depends on adjacent observations and does not by itself establish stationarity or a forecasting model.
Linear Regression and CAPM Evidence
The second lecture block connects the linear regression model to CAPM and financial return data.
Use this chapter to estimate a return relationship, interpret slope and intercept, and test residual assumptions Keep An estimated beta describes the sample relationship under the model; it is not a guaranteed causal effect or future constant.
Portfolio Performance and Multifactor Models
The third teaching block covers portfolio performance, multifactor CAPM and minimum-variance portfolios.
Use this chapter to combine asset or factor exposures and explain which component drives a performance difference Keep A performance measure is conditional on benchmark, horizon and risk model; changing any of them can change the ranking.
Autocorrelation and ARMA Forecasting
Weeks 4 and 5 introduce autocorrelation, partial autocorrelation, univariate models and forecasting with stationary ARMA processes.
Use this chapter to identify lag dependence, specify a parsimonious process and evaluate out-of-sample errors Keep A fitted time-series pattern may be unstable, and in-sample fit cannot substitute for forecast evaluation on information unavailable during estimation.
Trends, Unit Roots and Spurious Regression
The published sequence moves from forecasting into deterministic and stochastic trends, unit-root tests and spurious regression.
Use this chapter to diagnose non-stationarity and choose a transformation or test that matches the data-generating process Keep Detrending and differencing solve different problems; applying the wrong transformation can remove signal or leave stochastic persistence intact.
Conditional Volatility, VAR and Cointegration
The later subject sequence covers ARCH/GARCH, VAR, predictive causality, impulse responses and cointegration.
Use this chapter to separate volatility dynamics, predictive interaction and long-run equilibrium evidence Keep ARCH, VAR and cointegration answer different questions; one model’s significant coefficient cannot be imported as evidence for another mechanism.
Evidence and assessment control
The current Subject Guide publishes five weighted components totalling 100% and states that the end-of-semester examination must be passed.
Every percentage shown in the table comes from current official material.
Where a pass condition applies across tasks rather than to one component, it is stated separately instead of attaching an inaccurate hurdle badge to a row.
ECON90033 retrieval workshop
Worked check. Use define the data-generating object, specify the model, estimate or calculate transparently, diagnose assumptions and interpret at the supported horizon.
Write the decisive relationship, verify its boundary and explain what would change the conclusion.
Classification practice. Choose one chapter and identify the first decision its method controls.
Transfer practice. Change one fact and retrace the first affected relationship without discarding premises that remain valid.
Verification practice. Compare the final claim with its calculation, evidence and stated boundary before treating it as complete.
Use retrieval, transfer and repair
After reading a chapter, close the page and reconstruct the definitions, mechanism, check and boundary.
Change one fact, identify the first affected inference and repair only that step. This makes revision sensitive to the reason an answer works rather than merely familiar with its wording.
Model-selection audit
- 2Define the level, return and forecast target.
- 3Diagnose mean and persistence structure.
- 4Model conditional variance and evaluate forecasts.
Key terms
- Log Return
- Log return is the difference between adjacent log prices and adds across consecutive periods.
- Residual
- A residual is the observed outcome minus its fitted value in the estimated sample.
- Stationarity
- Stationarity describes stability of relevant distributional properties under the model conditions.
- Unit Root
- A unit root is a persistence structure in which shocks do not decay from the level.
- Conditional Variance
- Conditional variance is the variance of the next innovation given the current information set.
- Cointegration
- Cointegration is a stationary long-run combination of non-stationary variables.
ECON90033 FAQ
What is the first move in a difficult financial econometrics problem?
Identify the requested decision, list supplied facts, select the governing financial econometrics concept and show the relationship that changes the result. Finish by testing one boundary rather than adding unrelated detail.
When must I recheck financial econometrics deadlines?
Use the current LMS page and official timetable for financial econometrics. Published weights and stable concepts remain useful here, while operational dates and submission settings stay controlled by the live University system.
Why does active recall help with financial econometrics?
Reconstruct the financial econometrics chapter map without notes, apply model specification, diagnostics and forecast evaluation to a changed case, and record the first failed move. Correcting that move builds transfer better than rereading a polished answer.
Are any practice cases taken from University assessment?
The financial econometrics cases are independent study exercises designed to expose reasoning, calculation and boundary checks. They are not University questions, solutions, rubrics or predictions of what will be assessed.
Which elements belong in the final econometrics response?
For a financial econometrics response, state the classification or model, show the decisive working, interpret the result in context and name the assumption or evidence that could change it. Keep administrative claims tied to current University instructions.
Which evidence controls a changed Quantitative Analysis of Finance I case?
Use the facts supplied in the case, the governing Finance concept and the chapter boundary. If an administrative setting or date affects the answer, confirm that setting on the current University site before relying on it.
How to study for the exam
Recompute transformations and estimates, keep the information set visible, interpret every coefficient with units and assumptions, and test models on changed data.
Your AI Finance tutor for ECON90033
Stuck on a hard ECON90033 question? Sia is AskSia’s AI Finance tutor — ask any ECON90033 Quantitative Analysis of Finance I 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.
