Photo credit: The Becker Friedman Institute
My previous 12 econometrics courses were standard courses. After a brief introduction or review of mathematical and statistical principles and rules, the course focused on the Classical Linear Regression Assumptions and then systematically addressed the common violations of these assumptions. For each violation (ex. heterskedasticity), I defined the violation, noted the issued caused, reviewed methods of detection, and offered solutions (if possible) for the problem. If time in the semester remained, I covered linear probability and probit models. Rarely was there time for time series analysis. Assessment consisted of two tests and a final, several homework sets, and an empirical paper. The paper was due in parts, beginning with a prospectus in the first few weeks of class, to incentivize working on the project throughout the semester rather than the final few weeks of the term.
Over these years I was frustrated with the average outcome of the course. On tests, students clearly were using memorization to prepare (ex. prove beta1-hat is an unbiased estimator for beta1 in a SLR model) and struggled with interpretation and thinking creatively. For homeworks, I suspect students spent a significant amount of time searching for answers to textbook problems and others online rather than working through them and learning the material. The empirical paper was the best learning tool and most students surprised themselves with what they could do and what they had learned. Still, I remained unsatisfied with the course structure and outcomes and believed that the final papers could be much better. As mentioned in the first post on this blog, reading "Undergraduate Econometrics Instruction: Through Our Classes, Darkly" both pinpointed the trouble in my course and gave me the courage to try something new. Angrist and Pischke's abstract states: "The past half‐century has seen economic research become increasingly empirical, while the nature of empirical economic research has also changed. In the 1960s and 1970s, an empirical economist’s typical mission was to “explain” economic variables like wages or GDP growth. Applied econometrics has since evolved to prioritize the estimation of specific causal effects and empirical policy analysis over general models of outcome determination. Yet econometric instruction remains mostly abstract, focusing on the search for “true models” and technical concerns associated with classical regression assumptions. Questions of research design and causality still take a back seat in the classroom, in spite of having risen to the top of the modern empirical agenda. This essay traces the divergent development of econometric teaching and empirical practice, arguing for a pedagogical paradigm shift." My fall 2017 econometrics course will move away from focusing on the "true model" and the "technical concerns associated with classical regression assumptions" and move towards the doing of econometrics. After a review of mathematical and statistical concepts needed for the course, we will focus on the major methods used by economists today: randomized trials, regression, IV, regression discontinuity designs, and differences-in-differences. In each section students will read published journal articles that employ a particular method and use data sets to apply the methods and interpret the results. Homework sets and tests will largely be application and interpretation which will hopefully incentivize students to move away from rote memorization. The empirical paper, which will still be assigned in pieces, will remain the focus assignment, but will hopefully take on more meaning for the students as they see published work by others, the power of the econometric methods, and develop experience in using these methods. As with any major curricular change, it will take time to work the kinks out and get my materials developed. I am excited about the challenge and the learning experience for the students. **You can see the latest version of the course syllabus on the "Lecture Notes". **
0 Comments
|
AuthorFull professor of economics at a small liberal arts college in Virginia taking the leap and going textbook-less in an undergraduate econometrics course. Archives
September 2018
Categories
All
|