From the course: Machine Learning and AI Foundations: Prediction, Causation, and Statistical Inference

Prediction, causation, and statistical inference

From the course: Machine Learning and AI Foundations: Prediction, Causation, and Statistical Inference

Start my 1-month free trial Buy for my team

Prediction, causation, and statistical inference

“

- [Keith] If you are a data scientist who got your start in machine learning, statistics may at times seem like a collection of elaborate rules that may or may not apply to machine learning. However, if you're a data scientist who got your start in statistics, some machine learning may seem like tennis being played without a net. And frustratingly, neither of them make it very easy to prove that something caused something else. Hi, I'm Keith McCormick and before I started my machine learning career almost 25 years ago, three topics were competing for my attention, psychology, statistical research methods, and the philosophy of science. We will draw from all three to sort out how stats and machine learning are different, when to use each, and how to use all the tools at your disposal to be clear and persuasive when you share your results. We'll also briefly explore the tricky issue of causality. What is safe and not safe to conclude from your statistics and machine learning models, all with the ultimate goal of using them more effectively, making you more confident about what you can say about your data with certainty. We have an interesting journey in front of us, so let's begin.

Contents