AU kursuskatalog arkiv

Regression Analysis ( forår 2010 - 5 ECTS )

Rammer for udbud

• Uddannelsessprog: engelsk
• Niveau: COURSE LEVEL: Compulsory 4th semester course in the BSc (Econonomics and Management) program.  
• Semester/kvarter: SEMESTER FOR WHICH THE COURSE DESCRIPTION APPLIES: Spring 2010  
• Timer per uge: NUMBER OF HOURS PER WEEK: 4 lectures + 2 exercise sessions for 7 weeks.  
• Deltagerbegrænsning: RESTRICTIONS ON ADMISSION: None.  
• Undervisningssted: Århus
• Hovedområde: Det Samfundsvidenskabelige Fakultet
• Udbud ID: 17500

Formål

LEARNING OBJECTIVES:

The objectives of the course are that the participants can:
• formulate the multiple linear regression model and its underlying assumptions in matrix form
• estimate and interpret the parameters of multiple linear regressions
• describe the statistical properties of the estimated parameters
• apply hypothesis testing concerning the parameters of multiple regression models
• apply the estimated regression model to compute forecasts and to interpret the precision of these forecasts
• describe the consequences of multicollinearity, omitted variables, functional form misspecification, heteroskedasticity and autocorrelation in multiple regression models
• evaluate the adequacy of the estimated regression models by performing test for omitted variables, functional form misspecification as well as neglected heteroskedasticity and autocorrelation
• apply efficient estimation in regression models with heteroskedastic innovations
• interpret and evaluate autocorrelation and heteroskedastic consistent statistics
• apply statistical inference in dynamic multiple regressions.

Indhold

COURSE DESCRIPTION:

The course introduces the students to regression analysis and teaches them to apply basic statistical techniques to estimate key parameters in economic models for describing economic and operational relations. The course also covers use of various databases and statistical software, including PcGive and GiveWin for analysis of macroeconomic issues.

COURSE SUBJECT AREAS:

• Regression analysis with several explanatory variables.
• Model estimation and specification.
• Hypothesis testing in multiple regressions.
• Partial regression.
• Functional form, dummy variables and parameter stability.
• Heteroskedasticity.
• Autocorrelation and dynamic regression models.

Faglige forudsætninger

REQUIRED COURSES:

None.

Underviser

 Timo Teräsvirta

Undervisnings- og arbejdsform

TEACHING METHOD:

The lectures will cover various theoretical topics as well as empirical illustrations. The software package OxMetrics/PcGive will be used extensively in the lectures throughout the course.

English

Litteratur

LITERATURE

• Heij, C., P. de Boer, P.H. Franses, T. Kloek & H.K. van Dijk (2004). Econometric Methods with Applications in Business and Economics. Oxford University Press, Ch. 3, pp. 117-186, Ch. 5, pp. 273-378, 386-388. . The total number of pages of required reading in Heij et al equals about 176 pages.
• Various notes, approximately 50 pages.

The total number of pages of required reading for the course equals approximately 230.

Studieordning og bedømmelse

Bacheloruddannelsen i økonomi

• Skriftlig, bedømt efter 7-skala med intern censur

FORM OF ASSESSMENT:

A 4-hour written exam jointly with Surveys and Qualitative Data. Students who are not taking Surveys and Qualitative Data will only take a 2 hour-written exam in Regression Analysis. An approved obligatory assignment is a requirement to take the exam.

The obligatory assignment will be handed out and solved during the last week of the course. The obligatory assignment can be solved in groups of up to 4 persons.

EXAMINATION AIDS ALLOWED: All - except any means of electronic communication including PCs.