ECON 522 Advanced Econometrics College of Business and Economics Course Syllabus Spring 2017

Transcription

1 ECON 522 Advanced Econometrics College of Business and Economics Course Syllabus Spring 2017 Course Time and Location: Tu&Th 3:00-4:15pm (Lecture), Location MBEB 3247 (except for Feb. 28) Th 1:30-2:45pm (Lab), Location MBEB 3247 Instructor: Dr. Kelly Chen Office Hours: W&F 1-2pm or by appointment Office Location: MBEB 3205 Phone: (208) A mathematician, a theoretical economist, and an econometrician are asked to find a black cat (who doesn t really exist) in a closed room with the lights off. The mathematician gets crazy trying to find a black cat that doesn t exist inside the darkened room and ends up in a psychiatric hospital. The theoretical economist is unable to catch the black cat that doesn t exist inside the darkened room, but exits the room proudly proclaiming that he can construct a model to describe all his movements with extreme accuracy. The econometrician walks securely into the darkened room, spends one hour looking for the black cat that doesn t exits and shouts from inside the room I ve caught it by the neck! Anonymous Course Overview and Objectives The purpose of this course is to expose you to econometric techniques frequently used by economists working with cross-sectional and/or panel data. The emphasis will be on the importance of research design for the identification of casual effects, as well as the limitations in the applicability of these techniques. Ten broad topics will be covered throughout the semester: 1) interpreting regressions, 2) panel data and correlated errors, 3) instrumental variables estimation, 4) experimental data, 5) differences-in-differences, 6) regression discontinuity design, 7) binary dependent variable and maximum likelihood estimation, and 8) censored/truncated data, and sample selection. Each topic will include an overview of the econometric theory, followed by model estiamtion using Stata, and discussion of papers that apply these models. I will lead the presentation of the theory and model estimations, and you will lead the paper discussions (see below). Correspondingly, you are expected to read the assigned papers, write a short summary on each of them before coming to lecture class meetings, and assess/discuss the quality and content of things you read and hear. Upon completion of this course, you will: Learn the most widely used econometrics models in our field; Develop skills of selecting appropriate data, estimating an econometric model, and communicating your results to a non-technical audience; Gain practical experience in using Stata for data management and model development; and Become more critical/skeptical consumers of empirical research in economics. Completing most problem sets in this course will require the use of Stata statistical software package. The version you need is Intercooled Stata (Stata/IC) or better; Small Stata will not suffice for our purposes. If you don t have easy access to a computer with Stata, you may want to consider renting this package for six-month (details here: Course prerequisites: ECON 521 Course requirements and grading schemes: There will be five problem sets, presentations of assigned papers, a midterm and a final exam at the end of the course. The final grade will consist of the following: 1

2 Presentations & Participation: 20% Problem Sets (5): 20% Midterm: 20% Final: 40% 1. Presentations & Participation: You will read 6-10 empirical papers applying the models we cover in class and write a short summary on each of them. The summary should include, but not necessarily limited to the following elements: i. What is the article s hypothesis and what are its main finding? ii. What are the primary cause and effect variables analyzed in the article? iii. What data was used in this study? iv. What is the primary estimating equation in the paper? v. What are the conditions under which it will generate unbiased and/or inconsistent estimate of the coefficient of interest? Try to emphasize the question and method of the paper more than the results. For each paper, one of you will be assigned to present the paper and your summary. The presentation should be minutes long, followed by inclass discussion. You should prepare slides for your presentation. The focus of your presentation should be on the econometric methods employed, whether you think the results are convincing, and why or why not. The nonpresenters are expected to participate in the discussion following each presentation. 2. Problem Sets: Five problem sets will be made available throughout the semester. They consist of two types of questions. The first are pencil to paper where you will calculate an estimate, derive an equation, interpret statistical results etc. The second type requires the use of Stata to perform computer exercises. Before each problem set is due, I will work through Stata examples in our lab sessions. You can then review the material and complete assignments outside of classroom. I encourage you to find a partner to work with so that if you run into problems, you can troubleshoot your code together. 3. Exams: There is one midterm and one final exam each consisting of a theoretical portion and a Stata portion. The two portions of an exam will be held in class during the same week. The theory exam will be closed-book and closed-notes. The applied/stata exam will be conducted in the lab or take-home, open-book and open-notes. The exams will cover material from the lectures and from the computer labs (such as writing code and interpreting the output from a regression in Stata). Make-up exams will be given only under special conditions, and you must request a make-up at least a week prior to the exam. Exceptions will be made only in the event of an emergency. You may be asked to provide evidence to substantiate the reason for your absence. Textbook and Readings: The principal textbook for this course is: James H. Stock and Mark W. Watson, Introduction to Econometrics, Updated, 3rd Edition, Pearson Education, Despite being an undergraduate textbook, Stock and Watson offers an interesting and easier introductory reading to a variety of econometrics topics. It also has a great companion website at that contains useful resources for students, including datasets and replication files used in examples and exercises presented in the book. Our lectures will also be supplemented with a few chapters from the following books: 2

3 Joshua D. Angrist and Jörn-Steffen Pischke, Mostly Harmless Econometrics: An Empiricist s Companion, Princeton University Press, Cameron, Adrian Colin. Microeconometrics Using Stata. College Station, Tex.: Stata Press, A couple of more good references that I also recommend are: Jeffrey M. Wooldridge, Introductory Econometrics, A Modern Approach, 5th edition, Southwestern, The book contains a comprehensive treatment of undergraduate econometrics. It is a bit more technical than Stock and Watson (2015), but most of the advanced mathematics is left as optional material. Cameron, A. Colin, and Pravin K. Trivedi. Microeconometrics: Methods and Applications. Cambridge University Press, This book covers both old (panel data, IV) and the new topics (bootstrapping, quantile regressions, clustered standard errors, etc.) and it has a nice blend of statistical intuition and mathematical rigor. In addition, we will go over a number of empirical papers that employ the methods discussed in class. About one third of them will be presented by you or your peers and you are expected to read them ahead of class in order to be prepared for their discussion: 1. Almond, D., Chay, K. Y., & Lee, D. S. (2005). The Costs of Low Birth Weight. The Quarterly Journal of Economics, 120(3), Angrist, J. D., & Krueger, A. B. (2001). Instrumental Variables and the Search for Identification: From Supply and Demand to Natural Experiments. The Journal of Economic Perspectives, 15(4), Stinebrickner, R., & Stinebrickner, T. R. (2008). The causal effect of studying on academic performance. The BE Journal of Economic Analysis & Policy, 8(1). 4. Hoxby, C. M. (2000). The Effects of Class Size on Student Achievement: New Evidence from Population Variation. The Quarterly Journal of Economics, 115(4), Angrist, J. D. (1990). Lifetime earnings and the Vietnam era draft lottery: evidence from social security administrative records. The American Economic Review, Levitt, Steven D. "The Effect of Prison Population Size on Crime Rates: Evidence from Prison Overcrowding Litigation." The Quarterly Journal of Economics (1996): Meyer, B. D. (1995). Natural and quasi-experiments in economics. Journal of business & economic statistics, 13(2), Rosenzweig, M. R., & Wolpin, K. I. (2000). Natural" natural experiments" in economics. Journal of Economic Literature, 38(4), Krueger, A. B. (1999). Experimental Estimates of Education Production Functions. Quarterly Journal of Economics, Fernald, L. C., Gertler, P. J., & Neufeld, L. M. (2008). Role of cash in conditional cash transfer programmes for child health, growth, and development: an analysis of Mexico's Oportunidades. The Lancet, 371 (9615), Fernald, L. C., Gertler, P. J., & Neufeld, L. M. (2009). 10-year effect of Oportunidades, Mexico's conditional cash transfer programme, on child growth, cognition, language, and behavior: a longitudinal follow-up study. The Lancet, 374(9706), Card, D., & Krueger, A. B. (1994). Minimum Wages and Employment: A Case Study of the Fast-Food Industry in New Jersey and Pennsylvania. The American Economic Review, 84(4), Card, D., & Krueger, A. B. (2000). Minimum wages and employment: a case study of the fast-food industry in New Jersey and Pennsylvania: reply. The American Economic Review, 90(5), Cohen, A., & Einav, L. (2003). The effects of mandatory seat belt laws on driving behavior and traffic fatalities. Review of Economics and Statistics, 85(4),

4 15. Akee, R. K., Copeland, W. E., Keeler, G., Angold, A., & Costello, E. J. (2010). Parents' incomes and children's outcomes: a quasi-experiment using transfer payments from casino profits. American Economic Journal: Applied Economics, 2(1), Imbens, G. W., & Lemieux, T. (2008). Regression discontinuity designs: A guide to practice. Journal of econometrics, 142(2), Matsudaira, J. D. (2008). Mandatory summer school and student achievement. Journal of Econometrics, 142(2), Angrist, J. D., & Lavy, V. (1999). Using Maimonides' Rule to Estimate the Effect of Class Size on Scholastic Achievement. The Quarterly Journal of Economics, 114(2), Krueger, A. B., & Malečková, J. (2003). Education, poverty and terrorism: Is there a causal connection?. The Journal of Economic Perspectives, 17(4), Evans, W. N., Farrelly, M. С., & Montgomery, E. (1999). Do Workplace Smoking Bans Reduce Smoking?. The American Economic Review, 89(4), Heckman, J., Ichimura, H., Smith, J., & Todd, P. (1998). Characterizing Selection Bias Using Experimental Data. Econometrica, 66(5), LaLonde, R. J. (1986). Evaluating the econometric evaluations of training programs with experimental data. The American economic review, Evans, W. N., & Farrelly, M. C. (1998). The compensating behavior of smokers: taxes, tar, and nicotine. The Rand journal of economics, Academic Dishonesty The penalty for any breach of the honor code is a zero for the problem set or exam. More severe offenses call for receiving a failing grade, being dismissed from the class, suspension, or expulsion. If you have questions about what constitutes academic dishonesty in general, please see the following link. If any questions arise about what is allowable in this class, please ask me. The link to BSU policy on academic honesty is: Disabilities If you have a disability that requires special accommodation in class, for assignments, exams or any other task, please come and see me by the second week of class. For information regarding disabilities and accommodations that the University can make for you see Course outline and readings: A preliminary outline of topics to be covered and related readings is presented below. 4

5 (Week) Dates Week 1 1/10 Week 1 1/12 Week 2-3 1/17, 1/19 & 1/24 Week 3-4 1/26, 1/31, & 2/2 Week 5-6 2/7, 2/9, 2/14 & 2/16 Lecture Topic Readings Lab Activity Deliverables Introduction Economic questions and data Correlation and causation Threats to external and internal validity Review of Probability Mean and variance Conditional probabilities and independence Sampling Review of Linear Regressions OLS estimation and assumptions Hypothesis tests: t and F Heteroskedasticity Collinear variables Polynomials, logarithm transformation and interactions Panel Data and Correlated Errors Before and after comparisons Fixed effects regression Clustered standard errors Instrumental Variables Regression Two stage least squares The general IV regression model Checking instrument validity Stock and Watson Ch. 1 and Ch. 8 Chetty, Raj (2013), Yes, Economics is a science, The New York Times 10/12/2013 Stock and Watson Ch. 2 Stock and Watson Ch. 4 Ch. 7 Angrist and Pischke Ch. 3 Wooldridge, Jeffrey (2009) Carrying out an Empirical Project, in Introductory Econometrics: A Modern Approach, 4 th Edition Stock and Watson Ch. 10 Angrist and Pischke Ch. 5.1 & 8 Almond, D., Chay, K. Y., & Lee, D. S. (2005). The Costs of Low Birth Weight. The Quarterly Journal of Economics, 120(3), Stock and Watson Ch. 12 Angrist and Pischke Ch. 4 Angrist, J. D., & Krueger, A. B. (2001). Instrumental Variables and the Search for Identification: From Supply and Demand to Natural Experiments. The Journal of Economic Perspectives, 15(4), Stinebrickner, R., & Stinebrickner, T. R. (2008). The causal effect of studying on academic performance. The BE Journal of Economic Analysis & Policy, 8(1). Introduction to Stata (Lab handout #1) Introduction to Stata (Lab handout #1); Linear Regression (Lab handout #2) Panel Data Methods (Lab handout #3) Instrumental Variables Estimation (Lab handout #4) Discussion on Wooldridge (2009) Almond (2005) Angrist (1990) and Levitt (1996) 5

6 Week 7 2/21 & 2/23 Midterm exam Hoxby, C. M. (2000). The Effects of Class Size on Student Achievement: New Evidence from Population Variation. The Quarterly Journal of Economics, 115(4), Angrist, J. D. (1990). Lifetime earnings and the Vietnam era draft lottery: evidence from social security administrative records. The American Economic Review, Levitt, Steven D. "The Effect of Prison Population Size on Crime Rates: Evidence from Prison Overcrowding Litigation." The Quarterly Journal of Economics (1996):

7 Week 8-9 2/28, 3/2 & 3/7 Experiments and Quasi-Experiments Idealized experiments and threats to validity of experiments Quasi-experiments and threats to validity of quasi-experiments Experimental and quasiexperimental estimates in Heterogeneous Populations Stock and Watson Ch. 13 Angrist and Pischke Ch. 2 Rosenzweig, M. R., & Wolpin, K. I. (2000). Natural" natural experiments" in economics. Journal of Economic Literature, 38(4), Rosenzweig, M. R., & Wolpin, K. I. (2000). Natural natural experiments" in economics. Journal of Economic Literature, 38(4), Krueger, A. B. (1999). Experimental Estimates of Education Production Functions. Quarterly Journal of Economics, Fernald, L. C., Gertler, P. J., & Neufeld, L. M. (2008). Role of cash in conditional cash transfer programmes for child health, growth, and development: an analysis of Mexico's Oportunidades. The Lancet, 371 (9615), Fernald, L. C., Gertler, P. J., & Neufeld, L. M. (2009). 10-year effect of Oportunidades, Mexico's conditional cash transfer programme, on child growth, cognition, language, and behavior: a longitudinal follow-up study. The Lancet, 374(9706), Experiments and Quasi- Experimental Data (Lab handout #5) Fernald et al. (2008) and (2009) Week /9, 3/14 & 3/16 Differences-in-Differences (DD) Program evaluation The DD estimator Problems with DD estimators DD with control variables DD with multiple time periods Angrist and Pischke Ch. 5.2 Card, D., & Krueger, A. B. (1994). Minimum Wages and Employment: A Case Study of the Fast-Food Industry in New Jersey and Pennsylvania. The American Economic Review, 84(4), Card, D., & Krueger, A. B. (2000). Minimum wages and employment: a case study of the fast-food industry in Experiments and Quasi- Experimental Data (Lab handout #5) Cohen and Einav (2003) and Akee et al. (2010) 7

8 Week 11 Week 12 3/28, 3/30 & 4/4 SPRING BREAK Regression Discontinuity Sharp RD Fuzzy RD New Jersey and Pennsylvania: reply. The American Economic Review, 90(5), Cohen, A., & Einav, L. (2003). The effects of mandatory seat belt laws on driving behavior and traffic fatalities. Review of Economics and Statistics, 85(4), Akee, R. K., Copeland, W. E., Keeler, G., Angold, A., & Costello, E. J. (2010). Parents' incomes and children's outcomes: a quasi-experiment using transfer payments from casino profits. American Economic Journal: Applied Economics, 2(1), Angrist and Pischke Ch. 6 Imbens, G. W., & Lemieux, T. (2008). Regression discontinuity designs: A guide to practice. Journal of econometrics, 142(2), Matsudaira, J. D. (2008). Mandatory summer school and student achievement. Journal of Econometrics, 142(2), Angrist, J. D., & Lavy, V. (1999). Using Maimonides' Rule to Estimate the Effect of Class Size on Scholastic Achievement. The Quarterly Journal of Economics, 114(2), Experiments and Quasi- Experimental Data (Lab handout #5) Angrist and Lavy (1999) Week /6, 4/11 & 4/13 Binary Dependent Variable and Maximum Likelihood Estimation Stock and Watson Ch. 11 Krueger, A. B., & Malečková, J. (2003). Education, poverty and terrorism: Is there a causal connection?. The Journal Models of Discrete and Limited Dependent Krueger and 8

9 Week /18, 4/20 & 4/25 Censored, Truncated Data, and Sample Selection of Economic Perspectives, 17(4), Evans, W. N., Farrelly, M. С., & Montgomery, E. (1999). Do Workplace Smoking Bans Reduce Smoking?. The American Economic Review, 89(4), Heckman, J., Ichimura, H., Smith, J., & Todd, P. (1998). Characterizing Selection Bias Using Experimental Data. Econometrica, 66(5), LaLonde, R. J. (1986). Evaluating the econometric evaluations of training programs with experimental data. The American economic review, Evans, W. N., & Farrelly, M. C. (1998). The compensating behavior of smokers: taxes, tar, and nicotine. The Rand journal of economics, Variables (Lab handout #6) Models of Discrete and Limited Dependent Variables (Lab handout #6) Malečková (2003) LaLonde (1986) Week 16 4/27 Final exam 9