Dr Tatiana Komarova 32L.4.24, Dr Vassilis Hajivassiliou 32L.4.23 and Dr Yike Wang 32L.4.26

This course is compulsory on the MRes/PhD in Finance. This course is available on the MRes/PhD in Economics and MRes/PhD in Management (Marketing). This course is not available as an outside option.

Students should have completed an undergraduate level course in econometrics and statistical theory. Linear algebra and multivariate calculus will be used frequently.

• First part [Inference, Classical- and Generalized Linear Regression] begins with methods of estimation and optimality, followed by an introduction to asymptotic theory. It proceeds with statistical inference and the trinity of classical testing (Wald, Likelihood Ratio, and Lagrange Multiplier). It then discusses the classical linear regression model and commences the discussion of violation of the classical assumptions by discussing the Generalized Linear Regression Model (heteroskedasticity and autocorrelation).
• Second part [Generalized Regression Methods] provides a further discussion of violations of the classical assumptions including measurement error, omitted variables, simultaneity, missing data; non-linear regression models and instrumental variables. It proceeds to the Generalized Method of Moments and efficient estimation methods under conditional moment restrictions. It also covers the topics of quantile regression and bootstrapping.
• Third part [Time-series, Panel-data, and Microeconometric Methods] begins with a discussion of Time-Series topics, including single equation theory for non-stationary variables; serially correlated errors with lagged dependent variables; unit roots; simultaneous equations for non-stationary variables; co-integration; and ARCH and GARCH models. It proceeds to Panel data methods such as fixed and random effects estimators and their extensions for applying to dynamic linear and non-linear panel data models. The next major topic presents models with Limited Dependent Variables.
• Final part [Specialized Econometric Methods] discusses simulation-based inference, nonlinear panel data, and duration models. Finally, it covers the topics of program evaluation, nonparametrics, kernel estimation, and differences in differences.

30 hours of lectures and 15 hours of classes in the MT. 30 hours of lectures and 15 hours of classes in the LT.

This course is delivered through a combination of classes and lectures totalling a minimum of 45 hours across Michaelmas Term and Lent Term. This year, some or all of this teaching will be delivered through a combination of virtual classes, live streamed (recorded) lectures, and some flipped content delivered as short online videos. Attendance at lectures and classes is compulsory.

Compulsory exercises are set for each class.

Lecture notes will be made available through the departmental website and in course-packs for each part of the course. Please note there is no set book for this course.

Recommended books are:

W H Greene, Econometric Analysis, 6th edn, Pearson Education;

R Davidson & J MacKinnon, Estimation and Inference in Econometrics, Oxford University Press, 1993;

P. Ruud, An Introduction to Classical Econometric Theory, Oxford University Press, 2000;

T Amemiya, Advanced Econometrics, Harvard University Press, 1985;

J Johnston, Econometric Methods, 3rd edn, McGraw Hill;

G Judge et al, A Course in Econometrics, Wiley, 1988;

G Maddala, Econometrics, McGraw Hill, 1977.

Online exam (100%, 4 hours 15 minutes) in the ST.

Some departments have produced short videos to introduce their courses. Please refer to the course selection videos index page for further information.