Dr Sandra Sequeira, Dr Joana Naritomi and Dr Diana Weinhold

This course is compulsory on the MSc in Economic Policy for International Development. This course is available on the MSc in Anthropology and Development, MSc in Development Management, MSc in Development Management (LSE and Sciences Po), MSc in Development Studies, MSc in Environmental Economics and Climate Change, MSc in Health and International Development, MSc in International Development and Humanitarian Emergencies, MSc in Political Economy of Late Development and MSc in Political Science (Political Science and Political Economy). This course is available with permission as an outside option to students on other programmes where regulations permit.

DV494 is the required prerequisite for the three ID Economic Development Policy courses, DV490, DV491 and DV492. The course is designed to be taken in tandem with DV490 in the AT, and/or alone in AT in advance of DV491 and/or DV492 in the WT.

DV494 can also be taken as a stand-alone course for students who would like training in quantitative methods for international development.

The purpose of DV494 is to prepare a broad range of students to consume and critically engage with quantitative analysis for international development.  Drawing upon applied papers from top academic journals in development economics and related disciplines, students will engage with the challenges of causal inference in settings where scarce data, omitted variables, reverse causality, and selection bias must be addressed.  We engage with empirical debates from across international development, with examples illustrating how creative quantitative research designs can contribute to our understanding of economic growth, poverty, inequality, cultural and historical processes, gender norms, private sector development, health and education, and government capacity, among other themes.

We begin with an introduction to the philosophy of classical hypothesis testing and multiple regression analysis. We then explore how these tools are used in practice for causal inference in the real world; students will be introduced to a range of research designs, including panel data with fixed effects, difference-in-differences, event studies, instrumental variables, regression discontinuity designs, matching and synthetic controls, and randomized controlled trials. We also briefly explore recent advances in big data, AI and machine learning in development research.

The emphasis of the course is on developing applied skills for sophisticated engagement with frontier quantitative analysis in international development; there are no prerequisites - we focus on teaching students from a broad range of backgrounds.  As we teach from the frontier of research in international development there are opportunities for students with backgrounds ranging from little or no statistics to those with degrees in quantitative disciplines to challenge and expand their methodological intuition and skills. 

While the primary focus of the course is on learning to read, understand and rigorously consume empirical research, a series of Stata exercises will also provide students with a basic introduction to data management and statistical modelling.

20 hours of lectures in the AT.

Optional weekly supplementary workshops and a series of Stata sessions may also be provided.

A series of weekly problem sets and Stata exercises in the AT will provide formative skill building

- Angrist, Joshua D., and Jörn-Steffen Pischke. Mastering Metrics: The Path from Cause to Effect. Princeton University Press, 2014.

- Cunningham, Scott. Causal inference: The mixtape. Yale University Press, 2021.

Problem sets (40%) in the AT.
Take-home assessment (60%) in January.