Prof Mark Schankerman and Dr Jeremiah Dittmar

This course is compulsory on the Double Master of Public Administration (LSE-Columbia), Double Master of Public Administration (LSE-University of Toronto), MPA in Data Science for Public Policy and Master of Public Administration. This course is available on the MPA Dual Degree (LSE and Hertie), MPA Dual Degree (LSE and NUS) and MPA Dual Degree (LSE and Tokyo). This course is not available as an outside option.

The course introduces students to regression-based methods used for the quantitative evaluation of public policies. The course introduces students to basic multiple regression analysis including hypothesis testing, modelling of non-linear relationships, and dummy variables. From there, the course covers a number of regression based evaluation methods to assess the causal effectiveness of policy interventions. These include the use of randomized experiments, natural or quasi-experiments, panel data, difference-in-differences estimation, instrumental variables, matching and regression discontinuity design.

This course is delivered through a combination of lectures and classes totalling a minimum of 60 hours across Autumn Term and Winter Term. 

Formative coursework will include weekly problem sets

Particularly useful textbooks are Joshua D. Angrist and Jom-Steffen Pischke, "Mastering Metrics"; James Stock & Mark Watson, "Introduction to Econometrics"; and Jeffrey Wooldridge, "Introductory Econometrics". The material in the textbooks will be complemented with recent research papers and chapters from other books.  A complementary text, which is also available in an online version, is Scott Cunningham's "Casual Inference: The Mixtape" which is a good reference to gain intuition about some of the core causal methods we will study. A full reading list will be distributed at the beginning of the course.

Exam (70%, duration: 3 hours, reading time: 15 minutes) in the spring exam period.
Presentation (10%), policy memo (10%) and continuous assessment (10%) in the WT.