Cause-effect relationships are at the heart of many important
questions in economic history: Did the slave trades (1400-1900) cause
economic underdevelopment in Africa? Did the invention of the steam
engine cause the industrial revolution? Did immigration to the United
States during the Age of Mass Migration (1850-1920) cause economic
prosperity? The purpose of this course is to introduce students to the
core methods for identifying cause-effect relationships in economic
history and to apply these methods in practice. The course will expose
students to the concept of causality and explain under which assumptions
causal effects can be identified. We will focus on so-called natural
experiments, in which individuals, regions or other units are similar in
many respects but differ with respect to the factors whose influences
we want to study.
The course will have a strong focus on applications and will emphasise problems that economists and economic historians encounter in practice when studying cause-effect relationships. The tutorials will discuss important empirical studies in quantitative economic history and will provide students with the opportunity to apply empirical methods hands-on using the statistical software Stata. While the applications are in economic history, the methods taught in the course are also widely applied in other
areas of economics.
Topics covered include:
1. The problem of causality and randomized control trials
2. Selection on observables and regression specification
3. IV estimation
4. Regression discontinuity
5. Differences-in-differences and panel data
Students should be familiar with basic regression analysis (OLS, univariate and multivariate regression, hypothesis testing), as taught in e.g. Introduction to Empirical Methods or Advanced Empirical Economics I.
The objective of this course is to introduce and practice the most important methods that are used in "quantitative" economic history ("cliometrics"). Students will be introduced to all relevant steps alongside the value chain of research in quantitative economic history: Identifying historical datasources, processing data, constructing datasets, data analysis, and interpretation of results.
The course will introduce participants to the basic toolkits employed in recent research in quantitative economic history and long-run growth. In a hands-on approach, most of the teaching will be conducted in computer based classes. Lectures will give brief introduction into the relevant methodology and provide the econometric foundations. Tutorials will provide the necessary applied knowledge to gather data, produce datasets and conduct data analysis.
To this end, the course will replicate the empirical analyses of existing scholarly research. The core parts of the class will allow students to replicate econometric analysis based on cross-sectional data as well as panel data. Students will learn to acquire data from historical sources, such as historical statistics and maps, and supplementary information from geographical data. To this end, students will get acquainted with basic statistical software such as Stata or R, as well as basic Geographic information systems Software such as ArcGIS or Q-GIS.
The course addresses Master students in History & Economics, Economics, International Economics and Governance, and Philosophy & Economics. Participation is limited to 20 students. Students of History & Economics will be admitted without exception. Remaining slots will be filled based on the sequence of registration. Basic knowledge of econometrics at the level of Empirical Economics I is required.
Interested students are asked to sign up with Richard Franke via email to email@example.com
Prerequisite: Knowledge of Economic Growth on the level of Weil, Economic Growth, Routledge, 3rd, 2012.
Knowledge of Econometrics on the level of Stock and Watson, Introduction to Econometrics, Pearson, 2nd/3rd, 2014.
The course aims to equip the students with the necessary quantitative tools (data acquisition, data preparation, econometric-software handling and running regressions) that will be helpful to conduct research in the field of quantitative economic history, e.g., in the course of a master thesis.
Term paper including own data analysis