Applied introduction to good empirical research and causal inference for social scientists and others analyzing social data. Designed to provide an introduction to some of the most commonly used quantitative techniques for causal inference in social data including: survey design and inference, regression and propensity score matching, instrumental variables, differences-in-differences, regression discontinuity designs, standard errors, and the analysis of big data. Applications: organizations, entrepreneurship, public policy, innovation, economics, online education, visual representations, communication, critique and design of figures, graphs. Does not explicitly cover social network structure or machine learning as these topics are well-covered elsewhere. Students work in groups and individually to design and carry out a small research project based on the use of analytics, large data sets, or other digital innovations related to business or other organizations. Students become acquainted with a variety of approaches to research design, and are helped to develop their own research projects. Course prioritizes a thorough substantively grounded understanding of assumptions over mathematical proofs and derivations. Aimed at PhD students, but open by permission to Master's students and to students in other Stanford programs with relevant coursework or experience in analytics and statistics.
3 units · Letter or Credit/No Credit
Applied introduction to good empirical research and causal inference for social scientists and others analyzing social data. Designed to provide an introduction to some of the most commonly used quantitative techniques for causal inference in social data including: survey design and inference, regression and propensity score matching, instrumental variables, differences-in-differences, regression discontinuity designs, standard errors, and the analysis of big data. Applications: organizations, entrepreneurship, public policy, innovation, economics, online education, visual representations, communication, critique and design of figures, graphs. Does not explicitly cover social network structure or machine learning as these topics are well-covered elsewhere. Students work in groups and individually to design and carry out a small research project based on the use of analytics, large data sets, or other digital innovations related to business or other organizations. Students become acquainted with a variety of approaches to research design, and are helped to develop their own research projects. Course prioritizes a thorough substantively grounded understanding of assumptions over mathematical proofs and derivations. Aimed at PhD students, but open by permission to Master's students and to students in other Stanford programs with relevant coursework or experience in analytics and statistics.
Offered in Autumn 2025 at Stanford University.