M03.6 CONNECT THE MECHANISM
Who is represented by the data?
In 1936 a magazine polled 2.4 million people and called the election for the wrong man. Learn why size can't fix a skewed sample, and how the world shifts under a model.
LESSON OVERVIEW14 min lesson
Lesson overview
In 1936 a magazine polled 2.4 million people and called the election for the wrong man. Learn why size can't fix a skewed sample, and how the world shifts under a model.
What you’ll explore
- Sampling and deployment conditions determine which population a model’s results describe; distribution shift can change inputs, labels, or their relationships.
GO TO THE SOURCE
Original explanations, connected to the research.
An Introduction to Statistical Learning — authors’ materialsDive into Deep Learning — environment and distribution shiftWhy the 1936 Literary Digest Poll Failed (Squire, 1988)The Parable of Google Flu: Traps in Big Data Analysis (Lazer et al., 2014)Suggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.