Dr. Momin Malik
In this talk, I give practical guidance about when it is appropriate to use machine learning for social science applications in place of statistical modeling, and when appropriate, how to set up the modeling. I follow this with a recorded-live demonstration in R that starts with exploratory analysis, and proceeds to contrast a "social statistics" approach to a dataset to a machine learning approach in order to illustrate differences (and similarities).
Momin is a methodologist who seeks to resolve the realist and positivist foundations of quantitative modeling—with its frequently oppressive implications—with the necessity of having a critical and constructivist lens for pursuing goals of social justice, specifically around applications of machine learning to social science, and in the use of large-scale digital trace data. He has an undergraduate degree in history of science from Harvard, a master's from the Oxford Internet Institute, and a PhD from Carnegie Mellon University's School of Computer Science. He is currently an affiliate at the Berkman Klein Center for Internet & Society at Harvard University.