|Estimating Econometric Models|
|Instructor:||Dr. Michael Johnson|
|Class Schedule:||Tuesdays and Thursdays 12:30 to 2:00pm|
|Important Course Pages|
FRE528 Applied Econometrics
This course covers advanced econometric methods and related econometric theories useful for economists working in the food and resource sectors. Topics can include instrument variables (IV) estimation, difference-in-difference estimation, panel data methods (basic models, dynamic panel model and difference-in-differences), and finally qualitative and limited dependent variable models. The focus of the course will be on the application of these methods in econometric modeling rather than on theoretical proofs.
- To learn various advanced econometric methods, estimation methods and related econometric theories
- To apply these methods to data or econometric modelling techniques to estimate models using real world data
- To be able to write a code in Stata to estimate econometric models and replicate results from published econometrics research
- To be capable of interpreting econometric estimates, analyzing the results and critically evaluating published econometric research that use advanced econometrics methods.
Goals of this course
The purpose of this course is to provide an understanding of some of the more important econometric models and applications that will benefit the MFRE students in a future professional or academic role. This course will focus on 3 important areas of econometrics: IV estimation, Panel Methods and Qualitative/Limited Dependent Variables. As stated by Angrist and Pischke (2009), in their book Mostly Harmless Econometrics: An Empiricist's Companion, some of the most important items in an applied econometrician’s toolkit are: 1. Regression models designed to control for variables that mask the causal effects of interest; 2. Instrument variables methods for the analysis of real and natural experiments; and 3. Difference-in-difference-type strategies that control for unobserved omitted factors.
Your grade shall be determined as follows
|Evaluation||Date||Percent of grade|
|Final Exam||To be announced.||40%|
|Assignments||Assigned approximately every two weeks (see approximate schedule below).||30%|
|Team Paper presentation||To be announced.||20%|
|Class Participation||Contributions to class discussions.||10%|
Team-based learning will be applied in this course. The class participation grade depends on your contribution to class discussions and the overall learning environment. The sole aim of assigning a participation grade is to encourage active learning for everyone.
The assignments will consist of an applied problem that will allow the students to apply the various techniques and topics covered in class using real data sets. In addition, they will get practice in the use of the statistical software Stata.
Team Paper Presentations. Your team will research an applied research paper that utilizes econometric modeling based on one of the areas being discussed in this course. This is a form of mini-research project that is put together and presented to the class. The point of these presentations is to allow you to further become an expert in one of the studied areas and to share this knowledge with the class. The aim is to understand the integration of theory and the application of econometric models, by examining a research paper(s) that uses a particular econometric modeling technique and sharing it with the entire class. The presentation should summarize; critique as best as possible; and distill the essence of the research paper(s) and the econometric model(s) presented.
Please review the UBC Calendar “Academic regulations” for the university policy on cheating, plagiarism, and other forms of academic dishonesty. Academic dishonesty will be dealt with very seriously in this course.
Online Course Material
All materials will be posted through Canvas.
Textbook and Resources
A variety of journal publications (links provided later) will be discussed during class to strengthen a deeper understanding of the econometric models and its application to food and resource economics. Course materials will be drawn from a variety of textbooks:
Wooldridge, Jeffrey M., Basic Linear Unobserved Effects Panel Data Models (Chapter 10), Econometric Analysis of Cross Section and Panel Data, 2002.
R. Carter Hill, William E. Griffiths and Guay C. Lim, Principles of Econometrics (Chapters 10, 15 and 16), Fourth Edition, Wiley, 2011.
James H Stock and Mark Watson, Introduction to Econometrics (Chapters 10, 11, 12 and 13), 3/E, Pearson (2012).
Verbeek, M. (2012). A Modern Guide to Econometrics, Fourth Edition. John Wiley & Sons.
A Stata guide for the textbook is also on reserve at the same location: Using Stata for Principles of Econometrics, 4th edition by Lee C. Adkins and R. Carter Hill. 2011.
Tentative Lecture Schedule
Please Note: This is a tentative Lecture Schedule that may change.
|Week 1 Mar 27||Course Introduction; Endogeneity and start of IV Estimation.|
|Week 2 Mar 6||IV estimation (Applications to The Causal Effect of Studying on Academic Performance; Agricultural Supply and Demand; Consumerism application).
Hands-on exercise using IV estimation (wages and education) || Assignment 1 – IV Estimation
|Week 3 Mar 13||Experiments and quasi-experiments. Difference in difference estimation (waste disposal application). Analysis of Covariance (ANCOVA); Regression Discontinuity; Threats to Validity of Experiments.
Introduction to Panel Methods. First Differences Estimation (Application to training and product quality) ||
|Week 4 Mar 20||Panel Data – Fixed Effects Estimation (Policies relating to taxation and driving laws; Voting bias in sporting competitions).
Panel Data assumptions. Student Team Presentations. || Assignment 2 – Panel Data
|Week 5 Mar 27||Panel Data: Random Effects Models. Summary of panel methods/hands-on exercise.
Qualitative Dependent Variables models. Hands-on replication assignment: Determinants of Adoption of Improved Crossbred Cattles (Adoption of technology in agriculture) || Assignment 3 – LDV Models
|Week 6 April 6||Discrete choice (Multinomial logit for consumer decision making).
Team Presentations – final class. ||
|Final Exam - TBA|