Computational Historical Institutional Analysis

Machine learning (ML) and associated computational advances have opened entirely new avenues for processing and analyzing large datasets, especially those containing text. Drawing on pre-19th century England and related historical contexts, this applied course explores how the combined use of ML and conventional econometrics can facilitate new quantitative insights into the origins, change, and impact of institutions and culture. The applicable models, algorithms, and routines will be introduced intuitively as a means of addressing specific empirical problems or answering pertinent research questions. The course will alternate between lectures, in-class discussions of assigned readings, and shorter hands-on empirical exercises. Course participants are expected to possess a basic understanding of statistics, but there is no requirement of prior exposure to either ML or advanced econometrics.