杏吧论坛

Prof Valentino Larcinese

This course is available on the BA in Social Anthropology, BSc in History and Politics, BSc in Philosophy, Politics and Economics, BSc in Politics, BSc in Politics and Data Science, BSc in Politics and Economics, BSc in Politics and History, BSc in Politics and International Relations, BSc in Politics and Philosophy and BSc in Social Anthropology. This course is available as an outside option to students on other programmes where regulations permit and to General Course students.

This course will be freely available to students with the required background.

Students must have completed Quantitative Methods (Mathematics) (MA107) and Quantitative Methods (Statistics) (ST107), or equivalent courses.

This course provides an introduction to the most commonly used methods for causal inference in the social sciences using observational data. It covers simple and multiple regression (particularly focussing on the conditions for a causal interpretation of the coefficients), matching, panel data, diff-in-diff, instrumental variables, regression discontinuity. The course will prioritize the practical understanding and application of the methods rather than their statistical foundations. Applications will be selected from existing research literature.

This course is delivered through a combination of lectures and classes totalling a minimum of 30 hours in the Lent Term, with a reading week in LT Week 6.

Students will be expected to produce 1 problem set and 1 case study in the LT.

Stock & Watson: "Introduction to Econometrics", Pearson International (various editions, all equally valid)

Dunning: "Natural experiments in the social sciences", CUP 2012

Angrist & Pischke: "Mastering metrics", Princeton University Press 2015

Group project (60%) in the LT and ST.
Online assessment (40%) in the ST.

The group project includes a presentation element.

Online assessment duration: 7 days in the ST.