AØKB08026U  Econometrics B

Volume 2013/2014
Education
BSc. in Economics - mandatory
Content
During the course we go through the linear regression model, including specification, estimation, and testing of the model and the assumptions underlying it. The course mainly deals with analysis of cross section data, for example consisting of persons, households or companies, where individual observations can plausibly be assumed to be independent. Statistical methods for handling heterogeneous observations are introduced as well as methods allowing for integration of economic theory with the purpose of examining causal relationships.

There is emphasis on the implementation of the methods introduced. Exercise classes, where students get the opportunity to perform econometric analyses in practice are therefore an important part of the course. Moreover, in the lectures actual data sets will be widely used to illustrate various models.
Learning Outcome

The objective of the course is that students, after having completed the course, are able to

  • carry out a descriptive analysis of a data
  • give an account of the assumptions underlying the linear regression model for cross section data, including the necessary and sufficient conditions for obtaining consistent, unbiased and efficient estimates of the parameters of the model. Also, it is expected that the student can explain if these conditions are met in a specific application.
  • derive simple estimators and their properties and to carry out proofs for unbiasedness, consistency and efficiency
  • carry out estimation by the method of Ordinary Least Squares (OLS), Weighted Least Squares (WLS), Feasible Generalized least squares (FGLS), and Instrumental Variables estimation (IVE).
  • To carry out tests for misspecification (heteroscedasticity and functional form) and to give an account for their interpretation
  • To carry out and to give an account of tests of restrictions on parameters in a linear regression model (t- and F-tests, LM-test, Wald-test and heteroscedasticity consistent versions of these tests)
  • be able to interpret coefficients for different types of variables in a regression model (continuous variables, dummy variables, transformed variables)
  • apply estimated parameter estimates in a calculation based on a specific economic problem and to interpret the results
  • explain if a variable is exogenous or not exogenous and the reasons herefore.
  • carry out estimation for linear repeated cross section and panel data models based on data sets with two periods and to use such estimators for policy analysis.
  • be able to explain and carry out instrumental variables estimation on a specific data set
  • explain the correct use of proxy variables
  • apply econometric criteria for selecting a specific set of parameter estimates
  • be able to select and apply relevant techniques for analyzing new problems and data. This includes being able to identify characteristics of a data set, to propose and specify a relevant statistical model, to investigate to what extent the proposed statistical model give an adequate description of the data, to be able to estimate and interpret the parameters of the model, to report estimation results, to formulate economic questions as statistical hypotheses on the model parameters and to be able to test these hypotheses.

Pensum:

J.M. Wooldridge: Introductory Econometrics: A Modern Approach, 4th edition, 2009.
Chapter 1-9
Chapter 13 excl.: 13.5.
Chapter 15 excl. 15.7 and excl. page 535 line 16 from bottom - line. 9. from bottom.
Chapter 19
Appendix D
Appendix E excl.: page 807 (from beginning of E.4.) to page 809 line 5 from bottom.

Lecture Notes:

  • Note on Monte Carlo experiments (Mette Ejrnæs, Hans Christian Kongsted, Søren Leth-Petersen, September 2009)
  • Robust Covariance Matrix for OLS Estimates in Regression Models with Heteroscedasticity (Mette Ejrnæs, Hans Christian Kongsted, Søren Leth-Petersen, September 2009)
  • Notes on instrumental variables estimation (Mette Ejrnæs, Hans Christian Kongsted, May 2007)
Econometrics B is the second course in the compulsory statistics and econometrics sequence in the bachelor program, and it builds directly on Econometrics A. Participants are expected to have knowledge about basic statistical methods and probability theory corresponding to the syllabus of Econometrics A. We use mathematical tools, including matrix algebra, corresponding to what have been introduced in Mathematics in the first year.
4 hours of lectures and 3 hours of excercises per week for 14 weeks

The classes focus on doing exercises, including theoretical exercises as well as simulation exercises and estimation based on actual data sets. An integral part of the classes is to practice written communication of results obtained from an econometric analysis.
Credit
7,5 ECTS
Type of assessment
Written examination, 2 hours under invigilation
Written assignment, 30 hours
The exam consists of two parts:

(1) a written two-hour closed book exam
(2) a 30-hours take-home assignment. Students are encouraged to answer the assignment in groups consisting of maximally three members.
Exam registration requirements
To be able to register for the exam it is necessary to have passed the exam in Econometrics A or to have obtained similar documented qualifications elsewhere. Moreover, three compulsory exercise sets have to be completed satisfactory: (1) a two-hour test to be held in the examination-room at Peter Bangs Vej. This test has a format similar to the written closed-book exam. (2) two assignments where estimation based on an actual data set is to be carried out. This assignments has a format similar to the take-home exam.
Aid
All aids allowed
The two-hour examination is a closed book exam.
The 30-hour take-home assignment - all aids allowed.
Marking scale
7-point grading scale
Censorship form
External censorship
20 % external censurship
Exam period
Will be published at the begining of the semester
Re-exam
Same as ordinary. But if only a few students have registered for the re-exam, the exam might change to an oral exams with a synopsis to be handed in. This means that the examination date also will change.
Criteria for exam assesment
The Student must in a satisfactory way demonstrate that he/she has mastered the learning outcome of the course.
  • Category
  • Hours
  • Lectures
  • 56
  • Class Exercises
  • 42
  • Preparation
  • 76
  • Exam
  • 2
  • Exam
  • 30
  • Total
  • 206