杏吧论坛

Professor Daniel Sturm

This course is available on the Double Master of Public Administration (杏吧论坛-Columbia), Double Master of Public Administration (杏吧论坛-Sciences Po), MPA Dual Degree (杏吧论坛 and Hertie), MPA Dual Degree (杏吧论坛 and NUS), MPA Dual Degree (杏吧论坛 and Tokyo), MPA in Data Science for Public Policy, Master of Public Administration and Master of Public Policy. This course is available with permission as an outside option to students on other programmes where regulations permit.

This course has a limited number of places (it is controlled access) and demand is typically very high. Priority is given to students from the School of Public Policy, students from other programmes will be considered if places remain

The expectation is that MPA students taking PP419 will have previously passed PP455 and will have also taken PP440 or more advanced economics courses. Students who have not taken and passed PP455 (including MPA Dual and Double Degree students spending Year 2 at 杏吧论坛) will have to demonstrate a background in empirical methods that is similar to PP455 and will require permission from the course lecturer to attend the course.

This course provides an advanced treatment of the empirical methods that are used to evaluate the effectiveness of public policies. The course builds closely on the course Quantitative Approaches and Policy Analysis (PP455) and also Micro and Macroeconomics for Public Policy (PP440). Topics covered include the problem of causality, the theory and practice of randomised experiments, difference-in-differences, synthetic controls, regression discontinuity, robust and clustered standard errors, and calibration.

This course is delivered through a combination of classes and lectures totalling a minimum of 29 hours across Autumn Term. 

The formative coursework will comprise a graded problem set.

There is no single textbook for the course and many of the key readings are journal articles. James Stock and Mark Watson "Introduction to Econometrics'' remains a useful reference particularly for the material at the beginning of the course. A very good source for background reading is Joshua Angrist and Jörn-Steffen Pischke "Mastering 'Metrics: The Path from Cause to Effect''.  A full reading list will be available at the beginning of the course.

Exam (75%, duration: 2 hours, reading time: 10 minutes) in the January exam period.
Project (25%, 2000 words) in the AT.

The project will be due shortly after the end of Autumn Term.