Dr Filippo Boeri CKK 4.21

This course is compulsory on the MSc in Geographic Data Science. This course is available on the MPA in Data Science for Public Policy, MPhil/PhD in Economic Geography, MPhil/PhD in Regional and Urban Planning Studies, MSc in Environmental Economics and Climate Change, MSc in Environmental Policy, Technology and Health (Environmental Economics and Climate Change) (LSE and Peking University), MSc in Local Economic Development, MSc in Regional And Urban Planning Studies, MSc in Statistics (Social Statistics), MSc in Statistics (Social Statistics) (Research) and MSc in Urban Policy (LSE and Sciences Po). This course is available with permission as an outside option to students on other programmes where regulations permit.

The number of students that can be accommodated is limited. Students requesting this course should provide information on their prior econometrics and statistics training and their motivation for study. If the course is over-subscribed, places will be allocated at the Department’s discretion based on this information and a waiting list may be created. For further details, please contact your relevant Programme Coordinator

Students must have a good understanding of statistics and applied micro-econometrics at an undergraduate level or, for example, have studied Applied Quantitative Methods (GY428) in Autumn term or another course which introduces topics such as instrumental variables and panel data methods. It is advisable to look at the first two key readings listed below before signing up for this course. Students who are comfortable working with computers, data and already have basic familiarity with STATA, R or other statistics/econometrics software will get the most out of this course.

The aim of the course is to develop the technical tools necessary to understand and analyse spatial economic and social phenomena and to apply quantitative techniques to analyse economic and social problems, processes and policies at the urban and regional scale. The course also uses Geographical Information Systems and other spatial computer applications for research purposes, but you should not expect to get a training in GIS from this course (GY476 provides a complementary GIS course).

Topics include: spatial weights, aggregation and smoothing methods; spatial econometric models and neighbourhood effects; answering causal questions in the spatial context; spatial interaction and discrete choice models; spatial cluster and point pattern analysis; inequality, competition and diversity; structural spatial economic models, applications of machine learning. Not all topics will be covered every year.

Much of the content will be covered by studying and replicating the results of research papers.

In the Department of Geography and Environment, teaching will be delivered through a combination of classes/seminars, pre-recorded lectures, live online lectures, in-person lectures and other supplementary interactive live activities.

This course is delivered through a combination of computer practical classes/seminars and lectures across the Winter Term.

There are opportunities for support for the second assignment in the ST.

This course includes a reading week in Week 6 of Winter Term.

Throughout the term, progress and understanding will be assessed by in-class exercises and quizzes.

A reading list and outline is available on Moodle. Important readings are

Gibbons, S., H.G Overman and E. Patacchini (2015) Spatial Methods, Ch. 3 in Duranton, G, J.V. Henderson and W. Strange (eds) Handbook of Urban and Regional Economics Vol 5a, Elsevier

Baum-Snow, N. and F. Ferreira (2015) Causal Inference in Urban Economics, Ch. 1 in Duranton, G, J.V. Henderson and W. Strange (eds) Handbook of Urban and Regional Economics Vol 5a, Elsevier

An overview of some topics is provided by: A Fotheringham, C Brunsdon; M Charlton, Quantitative Geography: Perspectives on Spatial Data Analysis. Sage Publications, 2000.

Project (70%, 2800 words) in the ST.
Coursework (30%, 1200 words) in the WT.

Assessment for this course is in two parts:

Exercise testing some of the key learning outcomes, typically a report in the style of a journal referee report providing a critical evaluation of a journal article. Deadline near end of WT. 1200 words. Weighting 30%.

Project proposal, data analysis exercise or other assignment. Deadline around end of ST. 2800 words. Weighting 70%