Duration: 3 hours per week - 13 weeks [ECTS: 6]

Course outline

• Matrix Algebra: Revision of the basic concepts of
• The Classical Linear Regression Model: The basic assumptions. The Ordinary Least Squares method, properties of Least Squares estimators, the Gauss-Markov theorem. The coefficient of determination (R2) as a measure of goodness of fit.
• Multiple linear regression models: estimation and testing (OLS estimates, maximum likelihood estimates, BLUE estimates)
• Normality: Testing the hypothesis of normality
• Heteroskedasticity (the nature of the problem, consequences, detection and remedial measures).
• Autocorrelation (the nature of the problem, consequences of using OLS in the presence of autocorrelation, detecting autocorrelation, remedial measures when the structure of autocorrelations is known and when ρ is not known).
• Multicollinearity (the nature of the problem, consequences, detection and remedial measures)
• Specification error (the nature of the problem, consequences, detection and remedial measures)
• Extension of the Linear model: Non-linear models and regression on dummy variables
• Using Matrix Algebra in regression