From Moneyball to hurricanes, from drug research to marketing e-mail blasts, models provide useful ways of looking at the world, predicting the future, and succeeding in our endeavors.
But the world is increasingly complex, with huge amounts of data being generated every minute, and models can oversimplify. So how do you continue to use models in an increasingly complex world?
In a lecture coming up at Lawrence Technological University, economist and social scientist Scott E. Page says, the answer is to use more and more models simultaneously to study the same problem.
Page will speak in LTU’s annual Harold Hotelling Memorial Lecture at 7 p.m. Oct. 29, in the Mary E. Marburger Science & Engineering Auditorium (Room S100 in Building 7 at www.ltu.edu/map.) He’ll pepper his talk on using many models with real-world examples, from predicting stock market collapses, to solving income equality, to understanding why oil tankers, mice, and elephants are the size they are.
“One of the things we know from 20 years of really good social science is that if you do a horse race between people’s gut instinct and models, models win,” Page said. “Models win in science, models win in public policy, models win in sports. But models are pretty simple, and the world we’re trying to make sense of is complex. The way around this is to use many models. You want to build a toolbox of a lot of lenses through which to see the world. You could look at a problem as an economist, as a physicist, as a biologist, or as an engineer, and each one of those gives you a different lens on the problem. It makes individuals and groups much wiser than they are when they use a single model.”
Page is the Leonid Hurwicz Collegiate Professor of Complex Systems, Political Science, and Economics at the University of Michigan. He earned a Bachelor of Arts in mathematics from the University of Michigan, a Master of Arts in mathematics from the University of Wisconsin-Madison, and a Master of Arts in managerial economics and a PhD in managerial economics and decision sciences, both from Northwestern University. He joined the UM faculty in 2000. He is also an external faculty member at the Santa Fe Institute, an independent research center studying complex systems.
Page is the author of “The Model Thinker,” the No. 1 Amazon best-seller in financial engineering. More than 1 million people have enrolled in his Coursera online course, Model Thinking, which gets a ranking of 4.8 out of 5 stars—100,000 are signed up for it this semester alone.
Several of Page’s presentations are available on YouTube. For an early version of a talk on model thinking from 2015, visit https://www.youtube.com/watch?v=FSDGo-X9bKM. For a more recent version sponsored by the credit reporting firm Experian, visit https://www.youtube.com/watch?v=Z3I5WhFt7TA.
The Harold Hotelling Memorial Lecture Series was founded to honor an esteemed scholar and colleague. Harold Hotelling (1945–2009) joined Lawrence Tech as an associate professor of economics in 1989 and taught courses in business law, business ethics, constitutional law, urban social issues, and law and economics. His life was marked by an unwavering dedication to his family, his church, his students, and his profession. Everyone who knew him benefited from his keen intellect, tireless devotion, quick wit, and wonderful sense of humor. Hotelling’s contributions to Lawrence Tech will always be remembered, but more importantly, he will be remembered as a great person and a dear friend.