AU kursuskatalog arkiv

4610: Econometrics II ( efterår 2011 - 10 ECTS )

Rammer for udbud

• Uddannelsessprog: engelsk
• Niveau: Elective MSc & IMSQE course
• Semester/kvarter: Autumn 2011  
• Timer per uge: 4 lectures 12 weeks. Occasionally a lecture will be used for exercises. Timetables can be found at: http://econ.au.dk/studies/teaching-and-examination/teaching/timetables/
• Deltagerbegrænsning:
• Undervisningssted: Århus
• Hovedområde: Det Samfundsvidenskabelige Fakultet
• Udbud ID: 31887

Formål

The objective of the course is to give the students the necessary tools to read and understand empirical research at advanced academic level. The students will also be face with the challenge of having to implement various estimation strategies and reproduce academic research though exercises and tutorials.

LEARNING OBJECTIVES:

After having followed the course the student should be able to:

Read academic research articles and explain which econometric methods the presented research utilizes. In particular the students should be able place the research methods in the broad scope of econometric methodology and assess the appropriateness of the presented research strategy. More concretely put, does the researcher select a sensible econometric approach to analyze the data at hand? Can the objects of interest be identified from model-data combination that is used in the research? Does the data satisfy the modeling assumptions of the research? Most importantly, what are the implications for the conclusions that researchers draw if some of these choices are not satisfied in reality?

To fulfill these objectives the students must be able to:

• Deduce what kind of causal conclusion that can be drawn from a given econometric model.
• Analyze the statistical behavior of estimators by formulating them as an m-estimator. Apply the results from m-estimation to maximum likelihood estimation, GMM estimation and nonlinear regression models.
• Decide if the model specification gives a satisfactory approximation of the data set.
• Compare model performance using model selection criteria.
• Understand when and why Bootstrap and resampling methods should be used to supplement inference based on large sample results. 
• Implementation the presented econometric methods in typical standard programming language such as Ox or Matlab. 
• Understand how semi- and nonparametric modeling supplement the pure parametric approach in econometrics modeling.

Indhold

COURSE DESCRIPTION:
The purpose of the course is to provide the student with a rigorous introduction to econometric analysis of economic data. We will discuss the concept of causality, identification of parameters of interest, estimation methods with special focus on GMM and test theory and estimation. After this general introduction we will focus on a number of topics. The course will cover practical issues such as how one should go about implementing the methods in a typical programming language.

COURSE SUBJECT AREAS:

Subjects cover in the course will most likely be included in the following list

• Issues related to identification and causality
• Analyze the statistical behavior of estimators by formulating them as an m-estimator. Apply the results from m-estimation to maximum likelihood estimation, GMM estimation and nonlinear regression models 
• Hypothesis Tests 
• Specification and Model selection 
• Bootstrap and resampling methods
• Numerical optimization and estimation implementation in typical standard programming language such as Ox or Matlab.  
• Semi- and nonparametric modeling. Primarily regression 
• Bayesian Methods

Faglige forudsætninger

3620: Econometrics I

Underviser

Asger Lunde

Undervisnings- og arbejdsform

Lectures and exercises, theoretical as well as empirical.

English

Litteratur

Cameron, A. C. and P. K. Trivedi (2005), Microeconometrics: Methods and Applications. Chapters 1-2, 4-11, 13 and appendix A.

Approx. 300 pages.

It should be stressed that in spite of the title of the textbook, that this is not a course in microeconometrics. It is a course in general econometric methods that serves as a foundation for the following more specific courses in mircoeconometrics and time series econometrics.

Journal papers:

• Exogeneity:
  Engle, R. F., Hendry, D. F. & Richard, J. F. (1983), ‘Exogeneity', Econometrica 51, 277-304.
  Ericsson, N. R. (1994), Testing exogeneity: An introduction, in N. R. Ericsson & J. S. Irons, eds, ‘Testing Exogeneity', Oxford University Press, chapter 1, pp. 3-38.
  
• Model Selection: 
  Hansen, P. R., Lunde, A. & Nason, J. M. (2011), ‘The model confidence set', Econometrica 79, 453-497.  
  Romano, J. P., Shaikh, A. M. & Wolf, M. (2008), ‘Formalized data snooping based on generalized error rates', Econometric Theory 24, 404-447.

Lecture notes, approx. 50 pages
Study guide, slide sets from lectures and exercises. 

Bedømmelse

• Skriftlig, bedømt efter 7-skala med intern censur
5 xxxxx

FORM OF ASSESSMENT: 4 hour written exam based on data and literature material distributed 48 hours before exam start.

EXAMINATION AIDS ALLOWED: All - students are required to bring a laptop and hand in their exam answer as a pdf produced using plain Latex, LyX or SWP.