This course will provide a solid grounding in recent developments in applied micro-econometrics, including state-of-the art methods of applied econometric analysis.
The course will combine both analytical and computer-based (data) material to enable students to gain practical experience in analysing a wide variety of econometric problems. It will also discuss how modern data science approaches can be used to answer important economic questions. Students will be reading various applied economic papers which apply the techniques being taught. Applications that will be considered include labour, development, industrial organisation and finance.
The topics include analysis of matching methods, identification of average, local average and marginal treatment effects using instrumental variables, regression discontinuity, randomised control experiments, post-estimation diagnostics, cross section and panel data with static and dynamic models, binary choice models and binary classification methods in machine learning, maximum likelihood estimation, ridge regression, lasso regression, and principal component regression.
Lectures are complemented with computing exercises using real data in R or Stata.
This course is ideal for advanced undergraduate students, graduate students, early-career academic researchers, and researchers in the public, private or non-profit sector.
Dates: 8 July – 26 July 2019
Lecturers: Dr Rachael Meager, Dr Tatiana Komarova and Dr Marcia Schafgans
Course full. Closed for applications.
Level: 300 level. Read more information on levels in our FAQs
Fees: Please see Fees and payments
Lectures: 36 hours
Classes: 18 hours
Assessment*: Two written examinations and one computer based-exercise
Typical credit**: 3-4 credits (US) 7.5 ECTS points (EU)
*Assessment is optional
**You will need to check with your home institution
For more information on exams and credit, read Teaching and assessment
Participants should have a knowledge of quantitative research methods or introductory statistics, up to linear regression analysis. We except participants to have completed an introductory economics course. In particular, the course will assume that participants have an understanding of statistical inference using t-tests and have prior experience of interpreting the results of multiple linear regression. We will review these topics briefly during the course.
Familiarity with linear algebra, calculus and statistical software R or Stata will be helpful but are not required.
In the first teaching block (five days), the topics will include:
- Overview of Statistical Reasoning, and Introduction to Causal Inference (potential outcomes model, SUTVA, ATE)
- Regression models: DID, FEs, IV and LATE
- Standard errors: serial correlation, clustering and the bootstrap
- Likelihood-based inference, Numerical optimisation in practice
- Binary and Limited Outcome Models, Introduction to GMM.
In the second teaching block (five days), the topics will include:
- Matching methods. Randomized control trials
- Regression discontinuity design. Regression kink design
- Post-estimations diagnostics (Goodness of fit, Tests for functional form, tests for normality of errors, Leverage, influential observations and test for outliers), quantile regression and Quantile treatment effects
- Panel data models (static and dynamic)
- Discrete response models. Machine learning classification methods.
In the final teaching block (two days), the topics will include:
- Big Data, Model selection, information criteria
- Ridge and Lasso Regression
- Principal Component Regression.
- Demonstrate a solid grounding in recent developments in applied micro-econometrics, including state-of-the art methods of applied econometric analysis and their suitability to answer important economic questions.
- Demonstrate facility with implementing the techniques covered in the course using statistical software on real-world datasets.
- Demonstrate ability to answer economic questions of interest by using applied econometrics techniques.
The LSE Department of Economics is one of the biggest and best in the world, with expertise across the full spectrum of mainstream economics. A long-standing commitment to remaining at the cutting edge of developments in the field has ensured the lasting impact of its work on the discipline as a whole. Almost every major intellectual development within Economics over the past fifty years has had input from members of the department, which counts ten Nobel Prize winners among its current and former staff and students. Alumni are employed in a wide range of national and international organisations, in government, international institutions, business and finance.
The Department of Economics is a leading research department, consistently ranked in the top 20 economics departments worldwide. This is reflected in the 2014 Research Assessment Exercise which recognised the Department's outstanding contribution to the field. According to the REF 2014 results, 56 per cent of the Department’s research output was graded 4 star (the highest category), indicating that it is 'world-leading'. A further 33 per cent was designated 'internationally excellent' (3 star).
On this three week intensive programme, you will engage with and learn from full-time lecturers from the LSE’s economics faculty.
- Josh Angrist and Steve Pischke, (2009), Mostly Harmless Econometrics, (Princeton University Press).
- Marno Verbeek, (2017), A Guide to Modern Econometrics, (Wiley).
- James Stock and Mark Watson, (2011), Introduction to Econometrics, (MIT Press).
- Gareth James, Daniela Witte, Trevor Hastie and Robert Tibshirani, (2017): An Introduction to Statistical Learning: With Application in R. (Springer). Available for free online.
*A more detailed reading list will be supplied prior to the start of the programme
**Course content, faculty and dates may be subject to change without prior notice