MFIN6201 Empirical Techniques and Application in Finance
The Complete Exam Bible · T3 2026MFIN6201 Overview
- UNSW Sydney
- Term 3 2026
- Postgraduate finance
- Cumulative final examination
MFIN6201 Empirical Techniques and Application in Finance is a postgraduate econometrics course at UNSW Sydney. The captured Term 3 2026 course shell describes a toolkit for giving quantitative answers to economic and financial questions.
- Assessment Continuous work and the final each contribute half.
- Core skill Connect every calculation to its identifying assumption.
- Exam method Show units, test language and the source of variation.
What you get in the full MFIN6201 Exam Bible
- 8 chapters, 30 pages — every examinable topic, week by week
- 21 original practice questions, each with a model answer in the Final Examination format
- 8 worked examples, solved the way MFIN6201 marks
- 8 computed figures, redrawn from the course’s own numbers
- Exam-morning plan for the Final Examination (50%) — 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 MFIN6201 is assessed
| Component | Weight | Format |
|---|---|---|
| Class participation | 5% | Credit linked to participation in the two midterm quizzes. |
| Homework | 5% | Individual submissions with solutions provided after submission. |
| Midterm Quiz 1 | 15% | Week 3, in class, invigilated and pen and paper; through Week 2 material. |
| Midterm Quiz 2 | 25% | Week 8, in class, invigilated and pen and paper; through Week 7 material. |
| Final Examination | 50% | Cumulative and invigilated; confirm current T3 delivery conditions on Moodle. |
What other students are asking about MFIN6201
- Where can I find lecture notes or study guides for MFIN6201 at UNSW?
- The MFIN6201 study guide in AskSia Library covers Empirical Techniques and Application in Finance 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 MFIN6201, and how much is it worth?
- Yes. In the offering this AskSia Library guide is built from, Final Examination carries 50% of the MFIN6201 mark; the full split is Class participation 5%, Homework 5%, Midterm Quiz 1 15%, Midterm Quiz 2 25%, Final Examination 50%.
- What does MFIN6201 cover on random sampling and estimator behaviour?
- In AskSia Library's MFIN6201 guide, the Random Sampling and Estimator Behaviour chapter explains sampling distributions, unbiasedness, precision and consistency.
- What does MFIN6201 cover on large samples and statistical inference?
- In AskSia Library's MFIN6201 guide, the Large Samples and Statistical Inference chapter explains large-sample laws, tests, p-values and confidence intervals.
- What does MFIN6201 cover on simple regression and ols?
- In AskSia Library's MFIN6201 guide, the Simple Regression and OLS chapter explains fitted lines, residuals, coefficient units and measures of fit.
What MFIN6201 covers
The course begins with probability, random variables and sampling, develops large-sample inference, then builds simple and multiple regression before confronting omitted-variable bias, model specification and instrumental variables. The thread across every chapter is the same: identify the target quantity, compute it carefully, and state the assumption that permits the interpretation.
Probability, Dependence and Conditioning
Random variables, moments, covariance, independence and conditional expectationThis chapter turns uncertain financial outcomes into distributions that can be analysed. It covers expected value, variance, standard deviation, joint and conditional distributions, covariance, correlation and independence.
- Expected values from discrete states
- Variance and standard deviation
- Joint and conditional distributions
- Covariance and correlation
- Independence and mean independence
- Law of iterated expectations
Random Sampling and Estimator Behaviour
Sampling distributions, unbiasedness, precision and consistencyThis chapter treats an estimator as a random variable across repeated samples. It distinguishes population parameters from sample statistics and separates unbiasedness, variance, standard error and consistency.
- Population and sample distinctions
- Sampling distributions
- Unbiasedness and precision
- Variance of the sample mean
- Square-root sample-size scaling
- Consistency under large samples
Large Samples and Statistical Inference
Large-sample laws, tests, p-values and confidence intervalsThis chapter connects the law of large numbers and central limit theorem to practical inference. It develops null and alternative hypotheses, test statistics, significance levels, p-values and confidence intervals.
- Law of large numbers
- Central limit theorem
- Null and alternative hypotheses
- Test statistics and p-values
- Significance levels
- Confidence interval inversion
Simple Regression and OLS
Fitted lines, residuals, coefficient units and measures of fitThis chapter explains how ordinary least squares estimates a one-regressor linear relationship. It distinguishes population coefficients, fitted values and residuals, then interprets the slope with units.
- Population regression model
- OLS objective
- Fitted values and residuals
- Slope and intercept interpretation
- R-squared
- Standard error of regression
Least Squares Assumptions and Inference
Conditional mean zero, sampling conditions, outliers and standard errorsThis chapter links least-squares assumptions to the estimator properties they support.
- Conditional mean zero
- Iid regression sampling
- Outlier conditions
- Unbiased OLS
- Heteroskedasticity
- Robust standard errors
Multiple Regression and Multicollinearity
Partial effects, dummy variables, redundancy and imprecisionThis chapter interprets coefficients in a multiple-regression model as partial effects with included regressors held fixed.
- Multiple regression model
- Ceteris-paribus coefficients
- Dummy-variable coding
- Perfect multicollinearity
- Imperfect multicollinearity
- Single-coefficient inference
Omitted Variables and Model Specification
Bias conditions, control choices and specification sensitivityThis chapter gives a two-condition test for omitted-variable bias and a sign rule for its direction. A missing factor must affect the outcome and correlate with the regressor for the standard bias channel to operate.
- Two OVB conditions
- Bias direction rule
- Control variables
- Conditional mean independence
- Bad controls and mediators
- Specification sensitivity
Instrumental Variables and Causal Evidence
Relevance, exogeneity, exclusion and two-stage reasoningThis chapter treats instrumental variables as a design for isolating exogenous movement in an endogenous regressor. Relevance links the instrument to treatment, while exogeneity and exclusion close unwanted paths to the outcome.
- Endogeneity problem
- Instrument relevance
- Instrument exogeneity
- Exclusion restriction
- Two-stage least squares
- Weak instruments
It starts by rebuilding the probability and statistics needed for empirical work: random variables, expectation, variance, covariance, conditional distributions, independence, random sampling and sampling distributions. Large-sample laws then support hypothesis tests, p-values, t-statistics and confidence intervals. The second half of the guide turns to regression.
You learn how ordinary least squares constructs a fitted line, how to interpret slopes and residuals with their units, and why measures of fit do not establish causal validity. Least-squares assumptions connect the data-generating process to unbiasedness and inference. Multiple regression introduces partial effects, control variables, dummy-variable coding and multicollinearity.
The final chapters focus on the hardest interpretive moves: determining whether an omitted factor biases a coefficient, choosing controls from a causal story, and defending an instrumental variable through relevance, exogeneity and exclusion. The official handbook groups assessment into Continuous Assessments worth 50% and a Final Examination worth 50%.
The teaching materials further describe participation, homework and two in-class midterm quizzes inside the continuous half. The final is cumulative and invigilated. Some captured review files were reused from Term 1, so their dates, rooms and permitted-material instructions are not presented as current T3 logistics. Use current Moodle and the UNSW examination timetable for those operational details.
This guide uses newly authored examples and drills while preserving the course's emphasis on calculation plus convincing explanation.
Worked example · free
A test statistic and confidence interval from one estimate
- +1Compute t=(0.007-0)/0.003=2.33.
- +1Compare 2.33 with the large-sample two-sided 5% critical value 1.96 and reject zero.
- +1Construct 0.007±1.96(0.003)=[0.00112,0.01288].
- +1State that zero is outside the interval, while economic importance still depends on units and context.
Key terms
- Expected value
- The probability-weighted centre of a random variable's distribution.
- Variance
- The expected squared distance of a random variable from its mean.
- Conditional expectation
- The mean of a variable after conditioning on specified information.
- Sampling distribution
- The distribution of an estimator across repeated samples drawn by the same rule.
- Unbiased estimator
- An estimator whose repeated-sample expectation equals its target parameter.
- Standard error
- The estimated standard deviation of an estimator's sampling distribution.
- Central limit theorem
- A result giving an approximately normal standardised sampling distribution in large samples.
- P-value
- The null-based probability of a statistic at least as extreme as the observed one.
- OLS residual
- The observed outcome minus its fitted value from the estimated regression.
- Conditional mean zero
- The requirement that the regression error averages to zero at every regressor value.
- Omitted-variable bias
- Slope distortion caused by omitting a factor related to both the regressor and outcome.
- Instrumental variable
- A source of relevant, exogenous variation used to identify an endogenous regressor's effect.
MFIN6201 FAQ
How difficult is this course?
The challenge is cumulative reasoning rather than heavy matrix algebra. Probability, sampling and inference feed directly into regression, while later questions ask you to diagnose assumptions and causal claims. Students need accurate calculations and short explanations that identify the condition supporting each result.
How is the course assessed?
The official handbook assigns 50% to Continuous Assessments and 50% to the Final Examination. The teaching materials unpack the continuous half into participation, homework and two midterm quizzes. The numeric rows sum to 100%, and no component-specific hurdle is flagged in the sources used here.
What is known about the final examination?
The teaching materials describe a cumulative, invigilated final worth 50%. An early slide left the delivery mode unsettled, and a captured review file carries Term 1 logistics. Confirm the current T3 time, venue, delivery mode and permitted materials on Moodle and the UNSW examination timetable.
What do the midterm quizzes test?
The course introduction places the quizzes in Weeks 3 and 8 and says they cover material through Weeks 2 and 7 respectively. The Week 8 review emphasises calculation, convincing explanations and variants of homework rather than copied questions, so transfer matters more than memorisation.
Are past papers available?
The captured folder includes one old midterm sample, not a past final paper. The course shell warns that its coverage differs from the current quiz. Use it only to understand multi-part calculation style, and rely on current homework, review guidance and Moodle announcements for scope.
What is the best way to revise?
Build a connected formula sheet organised by problem type, then practise each formula with a changed sign, unit or conditioning set. After every numerical answer, state the interpretation and the assumption that permits it. Finish with mixed problems linking sampling, inference, regression and identification.
Questions students ask in each MFIN6201 chapter
- Why does zero correlation not prove independence?
- Correlation measures linear dependence only. Variables can have a strong nonlinear relationship whose positive and negative linear components cancel, leaving correlation at zero. Independence is a broader distributional claim and therefore requires more than a covariance or correlation calculation. Chapter 01 · Probability, Dependence and Conditioning
- Can an unbiased estimate be wrong in one sample?
- Yes. Unbiasedness concerns the average estimate across repeated samples, not exact equality in every realised dataset. A single estimate can sit above or below the target even when the estimation rule is unbiased. Chapter 02 · Random Sampling and Estimator Behaviour
- What is the difference between the LLN and CLT?
- The law of large numbers supports convergence of a sample average toward the population mean. The central limit theorem describes the approximately normal shape of the centred and scaled sampling distribution, which supports large-sample tests and intervals. Chapter 03 · Large Samples and Statistical Inference
- What does an OLS slope mean?
- It is the predicted change in the outcome associated with a one-unit increase in the regressor. A complete interpretation gives both variable units and avoids causal wording unless the identifying assumptions or research design justify it. Chapter 04 · Simple Regression and OLS
- Why is conditional mean zero important?
- It prevents the regressor from moving systematically with omitted determinants inside the error. Under the remaining sampling conditions, this protects the OLS slope from repeated-sample bias and gives the association a defensible conditional interpretation. Chapter 05 · Least Squares Assumptions and Inference
- What changes in a multiple-regression slope?
- The coefficient becomes a conditional comparison: predicted outcome change for one unit of its regressor while the other included variables remain fixed. This can improve comparability, but it does not guarantee that unobserved confounding is gone. Chapter 06 · Multiple Regression and Multicollinearity
- When does an omitted variable create bias?
- The omitted factor must influence the outcome after accounting for the regressor and must be correlated with that regressor. If either link is absent, that factor does not create the standard omitted-variable bias in the target slope. Chapter 07 · Omitted Variables and Model Specification
- What makes an instrument valid?
- It must move the endogenous regressor, remain unrelated to omitted outcome determinants and have no direct or alternative route to the outcome. Relevance can be measured in the first stage, while exogeneity and exclusion require a credible design argument. Chapter 08 · Instrumental Variables and Causal Evidence
How to study for the exam
Revise in three passes. First, rebuild the calculation engines: probability moments, the variance and standard error of a sample mean, test statistics, confidence intervals, fitted values, residuals and partial effects. Keep units beside every coefficient and write the null value explicitly. Second, attach an assumption to each engine.
Independence removes covariance terms, conditional mean zero supports unbiased OLS, robust standard errors address heteroskedastic variance, and an instrument needs relevance plus a defensible exogeneity and exclusion story. Third, practise explanation under time pressure. State what is estimated, show the number, give the test decision in null-language, and separate statistical significance from financial importance.
Use the captured old midterm only for question shape because the course shell says its coverage differs. Rework homework as variants by changing a sign, scale or control set. Before the final, verify current logistics on Moodle because reused Term 1 files do not establish T3 dates or permitted materials.
The most valuable final check is causal: ask where the regressor variation came from and what omitted path could still connect it to the outcome.
Your AI Finance tutor for MFIN6201
Stuck on a hard MFIN6201 question? Sia is AskSia’s AI Finance tutor — ask any MFIN6201 Empirical Techniques and Application in Finance 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.