Abstract: 

Collision bias is the most treacherous error in statistics: it can be subtle, it is easy to induce it by accident, and the error it causes can be bigger than the effect you are trying to measure. It is the cause of Berkson's paradox, the low birthweight paradox, and the obesity paradox, among other famous historical errors. And it might be the cause of your next blunder! Although it is best known in epidemiology, it appears in other fields of science, engineering, and business.

In this talk, I will present examples of collision bias and show how it can be caused by a biased sampling process or induced by inappropriate statistical controls; and I will introduce causal diagrams as a tool for representing causal hypotheses and diagnosing collision bias.

Outline:

Example of collision bias in college admissions
Berkson's paradox in real life
The low birthweight paradox and its consequences
A twin paradox
The obesity paradox: 30 years of confusion, one diagram of clarity
Causal diagrams and colliders

Background Knowledge:

This talk is accessible to an audience with a basic background in statistics or data science.

Bio: 

Allen Downey is a Staff Scientist at DrivenData and professor emeritus at Olin College. He is the author of several books related to computer science and data science, including Think Python, Think Stats, Think Bayes, and Think Complexity. His blog, Probably Overthinking It, features articles about Bayesian statistics. He received his Ph.D. in Computer Science from U.C. Berkeley, and M.S. and B.S. degrees from MIT.