ECOM20001
Econometrics 1
Semester 2 2024
Subject Outline
Introduction
Welcome to ECOM 20001: Econometrics 1. In this subject, students will explore ways to use data to learn how the world works to inform. and evaluate business and government decision-making. In doing so, students will be trained in a state-of-the-art statistical program called R, which is invaluable for data analysis and in high demand in industry and government.
Subject Overview and Aims
This subject aims to introduce econometrics, which involves using data and statistical methods to estimate economic relationships, test economic theory, and predict the impact of policy. Topics include probability and statistics, single linear regression, multiple linear regression, non-linear regression, model internal and external validity, field and natural experiments, and time series models. Econometric methodology and application will be motivated and illustrated through applications to economics, accounting, finance, marketing, and management.
Learning Outcomes
Learning Outcomes and Generic Skills
To view the subject objectives and the generic skills you will develop through successful completion of this subject, please see the University Handbook:
https://handbook.unimelb.edu.au/2024/subjects/ecom20001
Eligibility and Requirements
To view the eligibility and requirements, including prerequisites, corequisites, recommended background knowledge and core participation requirements for this subject, please see the University Handbook:
https://handbook.unimelb.edu.au/2024/subjects/ecom20001/eligibility-and-requirements
Lecture Schedule
Week | Start Date | Topics | Required Reading |
1 | 22 Jul | Introduction, Probability and Statistics Subject intro, review of probability and statistics. | Ch. 2 pp. 55-91 Ch. 3 pp. 103-131 |
2 | 29 Jul | Single Linear Regression – Estimation Single linear regression, population true values, ordinary least squares estimator, model fit, standard error of the regression, Least Squares Assumptions #1, #2, #3, sampling distribution of the OLS estimator | Ch. 4, pp. 143-165 |
3 | 5 Aug | Single Linear Regression – Testing Hypothesis testing with OLS estimator, hypothesis testing examples, one-sided alternatives, confidence intervals with OLS estimators, dummy variables, homoskedasticity, heteroskedasticity, Gauss Markov Theorem | Ch. 5, pp. 179-195 |
4 | 12 Aug | Multiple Linear Regression – Estimation Omitted variable bias, multiple linear regression model, OLS estimator for multiple linear regression, Least Squares Assumptions #1, #2, #3, #4, sampling distribution of OLS estimators in multiple regression, multicollinearity, dummy variable trap | Ch. 6, pp. 211-235 |
5 | 19 Aug | Multiple Linear Regression – Testing Standard errors, hypothesis tests and confidence intervals for a single coefficient in multiple linear regression, test of joint hypotheses, overall regression F-statistic, homoskedasticity-only F-statistic, testing single restrictions involving multiple coefficients, confidence sets | Ch. 7, pp. 247-268 |
6 | 26 Aug | Multiple Linear Regression – Testing (cont.) Model specification, conditional mean independence, variable of interest and control variables, R-Squared, applications of multiple linear regression: evaluating policy, testing theory, exploring empirical relationships | No textbook readings, lecture notes only |
7 | 2 Sep | Nonlinear Regression Non-linear regression functions, strategies for building non- linear models, non-linear function of a single independent variable, quadratic regression, polynomial regression, logarithms, logarithmic regression, linear-log models, log- linear models, log-log models | Ch. 8, pp. 277-297 |
8 | 9 Sep | Nonlinear Regression (cont.) Control variables in non-linear models, combining polynomial and logarithmic regressions, using polynomial functions for policy-relevant calculations, interactions models: binary- binary, binary-continuous, continuous-continuous | Ch. 8, pp. 297-316 |
9 | 16 Sep | Nonlinear Regression (cont.), Assessing Studies Combining polynomial and logarithmic models with interactions, application of nonlinear model estimation and testing, internal and external validity, threats to interval validity, using regressions for forecasting | Ch. 9, pp. 330-355 |
Lecture Slides
Lecture slides will be placed on the LMS page for this subject one week before the next set of lectures.
Recorded Lectures
All lectures will be live-streamed and can be attended live virtually. We also provide modular topic-specific videos to complement recorded lectures.
Audio and video recordings of lectures delivered for this subject will be available for review. These recordings allow you to revise lectures during the semester or to review them in
preparation for the end-of-semester exam.
Recordings are not a substitute for attendance; rather, they are designed for revision. On rare occasions, the recordings can fail to occur due to technical reasons. In such cases, a
substitute recording will be made available if possible. Lectures are also designed to enable collaborative learning and feedback to consolidate understanding of subject material.
Tutorials
Tutorial / Workshop Times
Weekly, in-person tutorials commence in week 1. Tutorial material will be posted on the LMS site one week before a tutorial is run. Please refer to the University timetable or LMS for details on tutorials, their times, and locations.
Tutorial / Workshop Participation Requirements
Tutorials are designed to train you in econometrics through application and to prepare you for the final exam. Attendance is required, and tutors will record it for credit.
Tutorial Schedule
Week | Topics |
1 | Introduction to R |
2 | Visualising and Describing Data in R |
3 | Testing Means, p-values, Confidence Intervals |
4 | Single Linear Regression Estimation |
5 | Single Linear Regression Testing |
6 | Dummy Variables, Heteroskedasticity, Omitted Variables |
7 | Dummy Variable Trap, Multicollinearity |
8 | Joint Hypothesis Testing with Multiple Linear Regression |
9 | Polynomial Regression |
Non-Teaching Week: 23-27 September | |
10 | Logarithmic Regression, Interactions |
11 | Combining Logarithmic Regression and Interactions |
12 | Time Series |
Timetable
MyTimetable is a class timetabling system that assists students in the creation of their individual timetable. This is done using a combination of student preference submissions and the provision of alternative options available where preferences cannot be fulfilled.
You will use this system to create your class timetable prior to each study period and you will have the opportunity to ‘self-register’ into suitable classes with availability or seek
assistance via a Timetable Assistance request form. Further information is available at: https://students.unimelb.edu.au/admin/class-timetable.
Private Tutoring Services
The Faculty has become increasingly concerned about the existence of a number of private tutoring services operating in Melbourne that heavily target University of Melbourne students enrolled in FBE subjects.
Students are urged to show caution and exercise their judgement if they are considering using any of these services, and to please take note of the following:
Any claim by any of these businesses that they have a “special” or “collaborative” or “partnership” style. relationship with the University or Faculty is false and misleading.
Any claim by a private tutoring service that they are in possession of, or can supply you with, forthcoming University exam or assignment questions or “insider” or “exclusive” information is also false and misleading.
The University has no relationship whatsoever with any of these services and takes these claims very seriously as they threaten to damage the University’s reputation and undermine its independence.
It is also not appropriate for students to provide course materials (including University
curricula, reading materials, exam and assignment questions and answers) to operators of these businesses for the purposes of allowing them to conduct commercial tutoring
activities. Doing so may amount to misconduct and will be taken seriously. Those materials contain intellectual property owned or controlled by the University.
We encourage you to bring to the attention of Faculty staff any behaviour or activity that is not aligned with University expectations or policy as outlined above.
Assessment
Assessment Overview
Your assessment for this subject comprises the following:
Assessment Task Individual/Group Due Date Weight
Assignment 1 (750 words) Group 16 Aug 2024 5%
Assignment 2 (750 words) Group 13 Sep 2024 5%
Assignment 3 (750 words) Group 18 Oct 2024 5%
12 Online Quizzes Individual Weekly, Weeks 1-12 10%
Tutorial Participation Individual Weekly, Weeks 1-12 5%
2-hour End-of-Semester Exam Individual During the exam period 70%
Hurdle requirement: To pass this subject students must pass the end of semester examination
Assessment Details
Assignments. These involve exam-type questions and data analysis using R. They can be submitted individually or in groups of up to 3 (max). Group members do not necessarily have to be from the same tutorial. To receive credit for the assignment, all group members must have their name and student number on the cover page. Students must confirm their
groups by 2 pm (AEST) Friday, two weeks before each assignment's due date. After this deadline, students not in a confirmed group will submit an assignment individually.
Quizzes. Partway through each lecture, a quiz question will be asked to the class, and they will need to reply within the allocated time to earn credit. Each weekly quiz has 2 questions (one in each lecture), such that students will effectively receive a mark out of 2 for each
weekly quiz. To maximize quiz scores for students, we will add up scores for all 24
questions and take the score out of 20 (with a max of 100%) to obtain your final quiz grade. Because you can miss or not complete 4 quiz questions without penalty, this should cover excuses for missed quizzes except for severe medical circumstances with a doctor’s note.
Students will be notified before each lecture of the quiz topic so they can prepare, and they will be encouraged to work in groups in class to answer the quiz question for that lecture.
Tutorials. You must attend and participate in tutorials to earn your tutorial mark each week. Students only get a tutorial mark for attending the tutorial they are officially enrolled in (their ‘official’ tutorial). Students with a legitimate reason (such as illness) for attending a tutorial other than their official one (or being unable to attend any tutorial) can apply to have the
tutorial mark for that week transferred to the final exam by emailing the tutorial coordinator (Mr Chin Yong Quek) their documentary evidence such as a medical certificate within a
week of missing the official tutorial. Late requests or requests sent to tutors will not be considered. No more than two tutorial marks will be transferred for any student.
You can miss 2 tutorials without penalty throughout the semester. This should cover all
excuses for missed tutorials except for severe medical circumstances with a doctor’s note, as mentioned above. Please email [email protected] if you are providing a medical note for missing tutorials.
Final Exam. The final exam is 2 hours in duration and will involve multiple-choice questions (like quiz questions), problem-solving and econometric analyses (like assignments and
tutorials). An extensive exam bank from past final exams will be provided to help students study for the final.
Faculty Hurdle Requirement. Students must pass the final exam to pass this subject.
Assignment and Quiz Submission
Assignment submission. This is via the LMS Assignment Submission link for all written assignments. Assignments must be submitted by 2 pm (AEST) on their due dates.
Please note that you must keep a copy of your assignment after it has been submitted, as you must be able to produce a copy at the request of the teaching staff at any time after the submission due date.
Quiz submission. All answers to quiz questions must be submitted via the LMS Quiz
Submission link. Quiz answers must be submitted within the allocated time window within the lecture in which a quiz question is asked, with the class working on it together. If
attending lectures virtually through a live stream, students can submit their quizzes within the allocated quiz start and end time. However, they will have less access to working on them together with other students in the lecture theatre.