Econometrics Spring 2020 Syllabus PDF

Preview

Summary

Download Econometrics Spring 2020 Syllabus PDF

Description

ECON-UA 266 - 006 Intro to Econometrics Monday - Wednesday: 9:30AM-10:45AM Bldg: SILV - Room: 408 - Loc: Washington

Instructor: Sahar Parsa ([email protected]) Personal website: https://parsahar.github.io/personal.website/index.html Office Hours Location: 19th West 4th - Room 832 Office Hours: Wednesday 11AM - 1PM & 4PM - 6PM Teaching Assistant: Anne Schick ([email protected]) Recitation time and location: Section 007: Tuesday 9:30AM - 10:45AM at GCASL 369 Section 008: Thursday 9:30AM - 10:45AM at GCASL 369 Office Hours Location: 19th West 4th - Room 516 Office Hours: Tuesday 11AM - 1PM & Thursday 11AM - 1PM Teaching Assistant: Odhrain McCarthy ([email protected]) Recitation time and location: Section 09: Friday 2.00pm - 3.15pm Section 10: Friday 12.30pm - 1.45pm Both at 7 East 12Street, Fairchild Building, Room LL27 Office Hours Location: NYU Department of Economics, 8th Floor, Room 804 Office Hours: Provisionally set for Wednesday 2.30pm-4pm Course Description: This course is intended as an introduction to modern applied econometric methods for undergraduates. The purpose of this course is to familiarize you with the basic tools of data analysis that economists use to answer questions, such as the univariate linear regression model, the multivariate linear regression model, statistical inference, binary choice estimation methods, differences-in-differences, instrumental variables, regression-discontinuity designs. You will finish the course equipped with a workman’s familiarity with data handling and statistical programming, and—hopefully—a good understanding of the models and methods of applied econometrics. The course has three parts: Part I covers univariate regression analysis. Part II covers multivariate regression analysis. Part III focuses on internal validity and causal analysis. That’s a lot of ground to cover, so plan your time accordingly. The material will be covered in two complementary outlets: 1) During the lectures, held twice a week, you will cover the theoretical concepts. 2) During the recitations, you apply these theoretical concepts to concrete examples motivated by economic applications. The theoretical content builds on the earlier Statistics prerequisite (ECON-UA 18 or 20). Knowledge of probability and statistics at the level of ECON-UA 18 or 20 is assumed. In addition, matrix algebra will be used as the main tool of analysis. Optimization methods need to be mastered. Both, the theoretical properties of the estimators and the economic applications, are important in order to understand correctly when to use various estimators and how to estimate and perform inference within these models under various sampling schemes. We will cover the theoretical concepts 1

by using specific economic applications. You will further explore and deepen your understanding in the (almost) weekly assignments. You will use the programming language R. R is most conveniently interfaced through RStudio which provides further functionality. You will be instructed in R during recitations given the large amount of material to be covered in lectures.

The slides, problem sets, solutions, grades and extra resources will be posted on the https://newclasses.nyu.edu/po b698-405b-abc4-dbe31a97b7b0course’s page. Make sure to check the course’s page frequently.

Suggested Texbook: There is no specific required textbooks. I will use slides to facilitate the lectures and the slides will be posted the course website. You are expected to participate, take notes, complement these slides when needed during class. Although the slides will be based on a number textbooks such as J. Stock and M. Watson, Introduction to Econometrics (3rd ed.), Addison Wesley, 2011 (SW), Wooldridge. Introductory Econometrics: A Modern Approach (W), J. Angrist and J.S. Pischke, Mastering Metrics: The Path from Cause to Effect, Princeton University Press, 2014 (MM), and J. Angrist and J.S. Pischke, Mostly Harmless Econometrics, Princeton University Press, 2009 (MHE), I do not follow any textbooks specifically and/or religiously. The notes will mention other relevant references when necessary. Finding the right textbooks often depends on ones learning style and preference. This is my personal opinion about the textbooks I just mentioned: SW and W are seminal classic textbooks that will build the materials rigorously with both breath and depth of knowledge. MM and MHE are particularly intuitive and relevant to cover the more advanced topics of internal validity and causal analysis. They give very concrete examples guiding the readers. Finally, more advanced but useful, Greene will cover the same material as SW and W, but the expositions tend to be more dry. Prerequisite(s): Mathematics for Economics II (MATH-UA 212), plus either Statistics (ECONUA 18) or Analytical Statistics (ECON-UA 20). The course is not open to any student who has taken Topics in Econometrics (ECON-UA 380).

Course Objectives: At the completion of this course, students will be able to: 1. 2. 3. 4.

understand the theoretical foundations of econometrics think critically about the difference between correlation and causation run regression, interpret the models and test hypothesis design their own empirical model with time and effor (and sometimes by reaching out to new materials) 5. understand applied work and communicate it to others

Grade Distribution:

10 Assignments 25% Recitation Participation 15% Exam I (2 March 2020) 20% Exam II (8 April 2020) 20% Exam III (11 May 2020) 20%

2

Problem Sets The problem sets are due on Fridays by 5PM, and only the 9 out of 10 best grades will count. Logistics: Problem sets are posted on NYU Class under Assignments. They are due on Fridays by 5pm on the course website, according to the attached course schedule. If you can’t upload the homework on time due to technical difficulties, send an email before the due time to the TA. If no email was sent before the due time, the late homework won’t be graded and you will get a zero. Make sure to not leave everything last minute. Students should solve each problem set and turn in their work by the specified due date. Students are strongly encouraged to work together on problem sets, but each student should write their own solutions. Feedback: Complete solutions to all problems are posted on NYU Class. Marked problem sets are returned during recitation. If you take a snap shot of your work before handing it in you can compare your answers to the posted solutions with your reasoning still fresh in your mind. If you wish to receive more individual feedback on your homework, please visit the TAs or me during office hours. Policies: There are no make-up or extensions. However, the lowest score from your problem sets is dropped. You are encouraged to discuss the problems sets with your classmates, however you must hand-in your own original work.

Exams Three in-class exams will be given on March 2nd 2020, April 8th 2019 and May 11th 2020. If a student misses an exam due to an objectively verifiable, unavoidable emergency situation, the student will have the occasion to take a make-up exam. There will be only one make-up exam coordinated for all the students who missed their exams due to an objectively verifiable, unavoidable emergency situation. If a student misses the exam for any other reasons, the student receives zero points for the exam. Exam etiquette: Exams are closed book, notes or cheat sheets are not allowed. On the day of the exam, you will be asked to drop off your backpack and coat upon entering the room and to proceed to your seat with your ID card and a scientific calculator. We will provide blue books, pencils and pens. During exams, students will not be allowed to leave the room before the end of the test. Exams will draw on material from lectures, recitations, and the assignments.

Grading Errors are human. Everyone should check their grades after receiving their scores. If a student finds an error in the grading of a problem set or exam, the student should contact me within one week of the day the graded problem sets or exams were made available by email with specific explanation for each question that needs to be regraded. We will then regrade the entire problem set or exam, and your total score may increase or decrease as a result.

Other Resources: Recitation Sessions: A recitation session is offered each week. These sessions are integral to the course and offer you a good opportunity to practice your analytical, problem-solving, and communication skills. See information at the beginning of syllabus for the recitations schedules and locations as well as information about the TA.

3

Office hours: If you need clarifications on the material covered in class or in recitation, you can attend one of the two walk-in office hours offered each week according to the schedule posted on NYU Classes, also found in this syllabus. Communication: All relevant materials and information will be posted on NYU Classes. All announcements will be broadcasted to your NYU email account. Check this frequently, or activate the automatic forward to a frequently checked account. You can also send me or the TA emails. I will try to get back to you on the same day. But sometimes it might take me longer up to three days max. I will answer your emails either by email or in person. When your questions are relevant to the class, I might broadcast the answer to the NYU Class website or in class.

Course Policies: • General – Computers are not to be used unless instructed to do so. – Exams are closed book, notes or cheat sheets are not allowed. On the day of the exam, you will be asked to drop off your backpack and coat upon entering the room and to proceed to your seat with your ID card and a scientific calculator. We will provide blue books, pencils and pens. During exams, students will not be allowed to leave the room before the end of the test. – There will be one make-up quizz per exam. The dates will be set in advanced. • Grades and Exams – C- is the minimum passing grade at grad level. A is the highest grade, then A-, B+, ..... C, C-. F is a fail. – Policies: There are no make-up or extensions. However, the lowest score from your problem sets is dropped. You are encouraged to discuss the problems sets with your classmates, however you must hand-in your own original work. • Assignments – No late assignments will be accepted under any circumstances. • Attendance and Absences – Students are responsible for all missed work, regardless of the reason for absence. It is also the absentee’s responsibility to get all missing notes or materials. There are also responsible for taking notes. Students are not allowed to take pictures or record the class. – Students are not allowed to use their phone during class. • Disabilities and extra time The student needs to fill out an application to be considered for an accommodation (nyu.edu/students/communities-and-groups/students-with-disabilities/academic.html). The student will work with a disability specialist to come up with a reasonable accommodations. If the student receives an accommodation, the Center for Students with Disabilities will notify the course professor.

4

Tentative Course Outline: The weekly coverage might change as it depends on the progress of the class. Week

Content

Week 1

• Introduction: Motivation, Class logistics, Population, Sample, Statistics, Sampling distribution, • Part I - Univariate regression model: Population regression model

Week 2

• Part I - Univariate regression model: Ordinary Least Squares estimator (OLS). • Part I - Univariate regression model: Properties of OLS estimator, OLS assumptions, unbiased estimator, sampling distribution, large sample distribution, consistent estimator, standard errors. • Problem set 1 due

Week 3

• Part I - Univariate regression model: Properties of OLS estimator, OLS assumptions, unbiased estimator, sampling distribution, large sample distribution, consistent estimator, standard errors. • Part I - Univariate regression model: How to run a regression in R? Interpretation and economic significance. • Problem set 2 due

Week 4

• Part I - Univariate regression model: Statistical significance and hypothesis testing. • Problem set 3 due

Week 5

• Part I - Univariate regression model: Statistical significance and hypothesis testing and application. • Part II - Multivariate regression model: Motivation and population model • Problem set 4 due

Week 6

• Exam I • Part II - Multivariate regression model: OLS estimator, Frisch-Waugh theorem and algebraic properties

5

Week

Content

Week 7

• Part II - Multivariate regression model: 2 variables case, ommitted variable bias • Part II - Multivariate regression model: Properties of OLS estimator, Multicollinearity • Problem set 5 due

Week 8

• Part II - Multivariate regression model: Properties of OLS estimator, BLUE • Part II - Multivariate regression model: How to run a multivariate model in R? Interpretation. • Problem set 6 due

Week 9

• Part II - Multivariate regression model: Hypothesis testing • Part II - Multivariate regression model: Dummy variables, other transformations and interpretations. • Problem set 7 due

Week 10

• Part II - Multivariate regression model: Heteroscedasticity, clustered standard errors, weighted least squares. • Exam II

Week 11

• Part III - Causal Analysis and other models: Linear and non-linear probability model • Part III - Causal Analysis and other models: motivation, internal and external validity • Problem set 8 due

Week 12

• Part III - Causal Analysis and other models: instrumental variables/2SLS estimation. • Part III - Causal Analysis and other models: instrumental variables/2SLS estimation. • Problem set 9 due

Week 13

• Part III - Causal Analysis and other models: Panel data and fixed effect model • Part III - Causal Analysis and other models: Panel data and fixed effect model • Problem set 10 due

Week 14

• Part III - Causal Analysis and other models: difference in difference model or Regression discontinuities (if enough time) • Exam III

6...