24
Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 1/24 Murat DEMİRCİ and İnsan TUNALI 19 September 2017 Econ 311 – Introduction to Econometrics Lecture 1 This course is about: The statistical analysis of economic (and related) data From the Syllabus: Econometrics covers the tools and methods used in empirical investigations of economic phenomena. These are also useful for analyzing many practical problems that arise in fields related to Economics, such as Finance, Marketing, Management, Political Science, and Public Policy.

Murat DEMİRCİ and İnsan TUNALI - #hayalinikeşfethome.ku.edu.tr/~itunali/econ311/handouts/Week 1 L1... · 2017. 9. 14. · Introduction to Econometrics, Pearson, 2015 (Global -

  • Upload
    others

  • View
    2

  • Download
    0

Embed Size (px)

Citation preview

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 1/24

    Murat DEMİRCİ and İnsan TUNALI 19 September 2017 Econ 311 – Introduction to Econometrics Lecture 1

    This course is about:

    The statistical analysis of economic (and related) data

    From the Syllabus:

    Econometrics covers the tools and methods used in

    empirical investigations of economic phenomena.

    These are also useful for analyzing many practical problems that arise in fields related to Economics, such as Finance, Marketing,

    Management, Political Science, and Public Policy.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 2/24

    ECON 311 is the first course in econometrics. It is based on linear regression, the most widely used tool for systematic examination of data.

    These methods are developed further in ECON 313 (Econometric Methods for Cross-Section and Panel Data) and ECON 314 (Econometric Methods for Time-Series and Forecasting).

    The main objective of ECON 311 is to equip the students with practical knowledge of multiple regression: estimation, hypothesis testing, and interpretation of the findings.

    Applications are an essential part of the course, and will be implemented on the Koç University computer network, using STATA.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 3/24

    The main textbook is: James H. Stock and Mark M. Watson, Introduction to Econometrics, Pearson, 2015 (Global - Updated 3rd Edition).

    The auxiliary textbook (which is available in the Reserve Library) is: Arthur S. Goldberger, Introductory Econometrics,

    Harvard University Press, 1998. The prerequisites for ECON 311 are: CPAP, MATH 201 (Statistics), and ECON 201 (Intermediate Microeconomics).

    Students who got a grade of C− or below in MATH 201 are strongly advised to work independently to make up for any deficiency they have during the first two weeks of the semester.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 4/24

    Organization of the course: • ECON 311 is organized around two 75 min. lectures plus a 75

    min. problem session (PS) per week. • Students must attend the PS they are registered in. Exceptions

    may be granted, but permission from the instructors is required. • Weekly homework assignments will be given, but only some

    parts will be graded. • Short Quizzes (9 in total) based on homework assignments will

    be given in the PS.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 5/24

    Grading:

    The course grade will be assigned on the basis of:

    • Graded assignments (10%), • Two midterm exams (25% each), • Final exam (40%).

    The final exam will emphasize the third part of the course.

    Quizzes:

    • Provide opportunities for earning extra credit. Quiz grades can be added to exam scores!

    • Are based on the material in the weekly assignments. For details, see the last page of the syllabus.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 6/24

    Make-up policy:

    If a student misses a midterm exam and has a valid excuse, the makeup exam will be given within one week, including the following Saturday.

    Valid reasons for missing an exam include documented cases of illness, family emergencies and participation in extracurricular activities sanctioned by the Dean of Students.

    There are no makeups for makeups!

    … no makeups for quizzes! Rules governing academic conduct at Koç University (see syllabus) will be strictly enforced.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 7/24

    Pace of the course:

    A brief course outline, which lists the approximate schedule of topics and chapters to be covered, and the tentative exam dates is given on the second page of the syllabus.

    Information on class and office locations, hours, e-mail addresses of the instructor and TAs, etc. is also provided there.

    Handouts and weekly homework assignments will be posted on Blackboard-KU.

    Blackboard announcements and occasionally mass e-mail messages will be used to convey additional information.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 8/24

    Student responsibilities:

    Students who attend classes regularly, read the handouts before coming to class, read the text book soon after, and work on the weekly assignments will do well in the quizzes, and will be able to prepare for the exams without having to cut back on time devoted to other activities.

    Students who fail to keep up with the pace of the course by skipping classes, and not doing the reading and the homework assignments on a timely and regular basis should not expect to do well in the course.

    THE LAST PAGE OF THE SYLLABUS CONTAINS COURSE INFORMATION IN BOLOGNA FORMAT.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 9/24

    Teaching schedule:

    • Lectures: TuTh 10-11:15 and 14:30-15:45 (SOS B11) Please attend the section you are enrolled in, space is limited.

    • Problem Sessions: PS B: F 10-11:15 (CASE B33) PS C: F 13-14:15 (CASE B40) PS D: F 14:30-15:45 (CASE B41) PS A: M 17:30-18:45 (CASE B39)

    If you have a conflict, write to us. We will try to accommodate your request.

    • Office hours: TBA or by appointment. • TA offices/hrs. TBA.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 10/24

    Brief Overview of the Course

    Economics suggests important relationships, often with policy implications, but virtually never suggests quantitative magnitudes of causal effects.

    • What is the quantitative effect of reducing class size on student achievement?

    • How does another year of education change earnings?

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 11/24

    • What is the price elasticity of cigarettes?

    • What is the effect on output growth of a 1 percentage point increase in interest rates by the Central Bank?

    • What is the effect on housing prices of environmental improvements?

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 12/24

    This course is about using data to measure causal effects.

    • Ideally, we would like an experiment May not be feasible. How would you conduct an experiment to estimate the effect of class size on standardized test scores?

    • But almost always we only have observational (nonexperimental)

    data. o returns to education o cigarette prices o monetary policy

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 13/24

    In this course you will:

    • Learn methods for estimating causal effects using observational data;

    • Learn some tools that can be used for other purposes; for example, forecasting using time series data;

    • Focus on applications – theory is used only as needed to understand the whys of the methods;

    • Learn to evaluate the regression analysis of others – this means you will be able to read/understand empirical economics papers in other econ courses;

    • Get some hands-on experience with regression analysis in your problem sets.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 14/24

    Handout: Empirical Relations

    This example is from the auxiliary textbook: Arthur S. Goldberger, Introductory Econometrics, Harvard University Press, 1998.

    In its simplest form, Human Capital (HC) Theory posits that wages (y) increase with education (x).

    That is, y = f(x) where f’ > 0.

    What does the empirical evidence look like?

    Data graphed on the next page consist of 528 individual obs. on y = hourly wages, x = education (years of schooling).

    The survey was conducted in 1985.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 15/24

    Scatterplot of y vs. x:

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 16/24

    Remark: There is a distribution of wages for each level of education. That is, there are multiple y values for each value of x.

    Q. Why is there a “distribution” of wages at each level of education?

    A.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 17/24

    Q. How do we discover the “positively sloped” function that HC Theory refers to? Put differently, what does the theorist mean when s/he says “wage is an increasing function of education”?

    Hint: The theorist surely knows that factors other than education affect wages but wants to abstract from them.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 18/24

    A. Let’s try: “Mean wage given education is an increasing function of education.”

    ○ data point (“observation”) ♦ mean wage for a given level of education

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 19/24

    The “function” we obtain by calculating the mean wage at each level of education is called the “sample conditional mean function.”

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 20/24

    Q. Given the raw data, how would you calculate the sample conditional mean function (cmf) of wages given education?

    A. First sort the sample into subsamples according to the level of education, and then calculate the subsample mean (arithmetic average) of wages in each subsample. Finally, plot the subsample means against education.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 21/24

    Remark: Sample cmf of wage given education is not smooth like a mathematical function, but it captures the relation we are after: average wage seems to increase with education.

    Q. Can you suggest simpler representations which serve our aims? Hint: What is the simplest function that you can think of?

    Q. How will you find the best one?

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 22/24

    A. We can find the best fitting line using least squares regression.

    Remark: The dashed line is the average wage in the sample.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 23/24

    Q. Consider the conditional distributions of wage given education. We saw that the mean increases with education.

    Are there any other differences?

    A.

  • Econ 311 – Fall 2017, Week 1: Introduction Version: 14.09.2017 09:46 Page 24/24

    Some other noteworthy differences:

    • The spread (variance) of the conditional distribution of wages given education increases with education.

    • For some education values there are very few observations. In general subsample sizes vary with education.

    Exercise for Thursday: You took Math 201 (or equivalent) and acquired some data analytic capabilities. In particular you learned about descriptive (summary) statistics, linear regression, and studied graphs. Print the handout Data Analysis (posted on the course web page), study it and answer the questions. Bring it to class.

    The auxiliary textbook (which is available in the Reserve Library) is: