EC402     
Econometrics

This information is for the 2017/18 session.

Teacher responsible

Dr Vassilis Hajivassiliou 32L.4.23, Dr Tatiana Komarova 32L.4.24 and Dr Rachael Meager

Availability

This course is compulsory on the MSc in Economics, MSc in Economics (2 Year Programme) and MSc in Quantitative Economic History. This course is available on the MPA in European Policy-Making, MPA in International Development, MPA in Public Policy and Management, MPA in Public and Economic Policy, MPA in Public and Social Policy, MPA in Social Impact, MPhil/PhD in Accounting and MSc in Economics and Philosophy. This course is available with permission as an outside option to students on other programmes where regulations permit.

Pre-requisites

Students must have completed Introductory Course in Mathematics and Statistics (EC400).

Students should also have completed an undergraduate degree or equivalent in Economics and an introductory course in Econometrics.

In very exceptional circumstances, students may take this course without EC400 provided they meet the necessary requirements and have received approval from the course conveners (via a face to face meeting), the MSc Economics Programme Director and their own Programme Director. Contact the Department of Economics for more information (econ.msc@lse.ac.uk).

Course content

The course aims to present and illustrate the techniques of empirical investigation in economics.

  • Regression models with fixed regressors (simple and multiple). Least squares and other estimation methods. Goodness of fit and hypothesis testing.
  • Regression models with stochastic regressors.
  • Asymptotic theory and its application to the regression model. Large sample approximations.
  • The partitioned regression model, multicollinearitymisspecification, omitted and added variables, measurement errors.
  • Heteroskedasticity, autocorrelation, and generalized least squares.
  • Exogeneity, endogeneity, and instrumental variables.
  • Nonlinear regression modelling and Limited Dependent Variables models.
  • An introduction to Non-classical econometric inference.
  • Autoregressive and moving average representations of time series. Stationarity and invertibility.
  • Vector auto-regressions.
  • Unit roots and co-integration.
  • Estimating causal effects in panel data: differences in difference estimator, matching methods, and regression discontinuity.
  • Panel data and static models: fixed and random effect estimators, specification tests, measurement errors.
  • Panel data and dynamic models: generalized method of moments.
  • Binary choice models with heterogeneity.

Teaching

30 hours of lectures and 10 hours of classes in the MT. 30 hours of lectures and 10 hours of classes in the LT.

Formative coursework

Two marked assignments per term. Exercises are provided each week and are discussed in classes. In order to have any chance of completing the course successfully, these exercises must be attempted. Special test exercises will be set at three points during the year. These will be carefully marked and the results made available.

Indicative reading

J Johnston & J diNardo, Econometric Methods (4th edn) or W H Greene, Econometric Analysis (6th edn), James D. Hamilton, Time Series Analysis (1994), J Wooldridge, Econometric Analysis of Cross Section and Panel Data (2002), J Angrist and J Pischke, Mostly Harmless Econometrics (2009)

Assessment

Exam (50%, duration: 2 hours) in the LT week 0.
Exam (50%, duration: 2 hours) in the main exam period.

Key facts

Department: Economics

Total students 2016/17: 140

Average class size 2016/17: 15

Controlled access 2016/17: Yes

Lecture capture used 2016/17: Yes (MT & LT)

Value: One Unit

Guidelines for interpreting course guide information

Course survey results

(2013/14 - 2015/16 combined)

1 = "best" score, 5 = "worst" score

The scores below are average responses.

Response rate: 90%

Question

Average
response

Reading list (Q2.1)

2.6

Materials (Q2.3)

2.2

Course satisfied (Q2.4)

2.2

Lectures (Q2.5)

2.2

Integration (Q2.6)

2.7

Contact (Q2.7)

2.2

Feedback (Q2.8)

2.7

Recommend (Q2.9)

Yes

57%

Maybe

37%

No

6%